{"@context":"https://schema.org","@type":"NewsArticle","generatedAt":"2026-09-21T09:00:48.663Z","headline":"Fable 5.1 体验评测：Anthropic Is So Back（again）","description":"Every 发布 Fable 5.1 的体验评测文章，标题称 Anthropic Is So Back（Again）。正文未提供有效文本，具体评测内容以原文为准。","url":"https://www.aioga.com/news/cmtj29bdi03leroh99l1xccw0/","mainEntityOfPage":"https://www.aioga.com/news/cmtj29bdi03leroh99l1xccw0/","datePublished":"2026-09-01T19:29:04.000Z","dateModified":"2026-09-01T19:29:04.000Z","inLanguage":"zh-CN","publisher":{"@type":"NewsMediaOrganization","name":"Aioga","url":"https://www.aioga.com"},"citation":["https://every.to/vibe-check/fable-5-1-vibe-check","https://aihot.virxact.com/items/cmtj29bdi03leroh99l1xccw0"],"canonicalUrl":"https://www.aioga.com/news/cmtj29bdi03leroh99l1xccw0/","directAnswer":{"@type":"Answer","text":"Every 在约一周的测试后发布 Fable 5.1 体验评测，称其在编程、写作和知识工作任务中比 Fable 5 更强，同时更快、更易交流；文章还称，相似任务下其令牌用量约为 Opus 5 的一半。","url":"https://www.aioga.com/news/cmtj29bdi03leroh99l1xccw0/","dateCreated":"2026-09-01T19:29:04.000Z","author":{"@type":"Organization","@id":"https://www.aioga.com/authors/aioga-editorial/#editorial-team","name":"Aioga Editorial Team","url":"https://www.aioga.com/authors/aioga-editorial/"}},"evidence":[{"@type":"CreativeWork","name":"Every：最新文章（网页） source article","url":"https://every.to/vibe-check/fable-5-1-vibe-check","datePublished":"2026-09-01T19:29:04.000Z","provider":{"@type":"Organization","name":"Every：最新文章（网页）","url":"https://every.to/vibe-check/fable-5-1-vibe-check"}},{"@type":"CreativeWork","name":"AIHot archive record","url":"https://aihot.virxact.com/items/cmtj29bdi03leroh99l1xccw0","datePublished":"2026-09-01T19:29:04.000Z","provider":{"@type":"Organization","name":"AIHot","url":"https://aihot.virxact.com/items/cmtj29bdi03leroh99l1xccw0"}}],"aggregationSource":"Every：最新文章（网页）","originalPublisher":{"name":"Every：最新文章（网页）","url":"https://every.to/vibe-check/fable-5-1-vibe-check"},"geoDeepAnswer":null,"article":{"id":"cmtj29bdi03leroh99l1xccw0","slug":"cmtj29bdi03leroh99l1xccw0","url":"https://www.aioga.com/news/cmtj29bdi03leroh99l1xccw0/","title":"Fable 5.1 体验评测：Anthropic Is So Back（again）","title_en":"","summary":"Every 发布 Fable 5.1 的体验评测文章，标题称 Anthropic Is So Back（Again）。正文未提供有效文本，具体评测内容以原文为准。","source":"Every：最新文章（网页）","sourceUrl":"https://every.to/vibe-check/fable-5-1-vibe-check","aiHotUrl":"https://aihot.virxact.com/items/cmtj29bdi03leroh99l1xccw0","publishedAt":"2026-09-01T19:29:04.000Z","category":"行业动态","score":58,"selected":false,"articleBody":["Fast, friendly, and even more powerful than its predecessor","We called the first Fable：/vibe-check/anthropic-mythos-our-fable-vibe-check a “warp drive” because it was the most powerful coding model we’d ever tested. But it was slow and hard to understand—it felt like a power tool only for the most AI-pilled of users.","In our testing it’s more powerful than Fable 5, running for days at a time to tackle coding challenges that stumped its predecessor. But it’s also fast and friendly, and, importantly, it speaks English like a normal person, er, AI. Unlike the original Fable and Anthropic’s recent Sonnet 5：/vibe-check/sonnet-5 and Opus 5：/vibe-check/opus-5 models, Anthropic has returned to form and created a model we actually enjoy talking to.","Oh, and there’s more: In our testing, it uses about half the tokens of Opus 5 for similar tasks. It should make Fable-level work available within an Opus budget. So it’s priced for everyone too.","Even more interesting, “everyone” now includes enterprises. Fable 5.1 comes with a zero-data retention option, removing a barrier that precluded most large companies from using it.","Fable 5.1 is a rare combination: the strongest coding model we’ve used and a collaborator we can recommend to people who don’t write code. It should be the first glimpse for most knowledge workers of truly delegated AI work—previously only the domain of programmers. You can give it a task like building a slide deck and move on to other things, confident that it’ll come back great in an hour or two.","We’ve been testing it for about a week, across coding, writing, and knowledge work tasks. Here’s our day-zero Vibe Check.","Anthropic says Fable 5.1 makes its strongest capabilities easier and cheaper to use. Its main claims:","Anthropic says the model can pursue a goal over extended runs and make better decisions about how to solve the underlying problem. Kieran’s experience supports that: Compared with Fable 5 on a task to build a clone of Every’s document editor Proof from scratch, it went deeper, added useful details he hadn’t requested, and showed better judgment about what worked.","Anthropic promises less stock phrasing, shorter updates, and closer attention to writing instructions. We saw this too: Its writing had fewer AI tells, and the team found its explanations easier to follow. It still routinely exceeded requested word counts.","Anthropic says Low and Medium can deliver performance at least as good as Fable 5 at substantially lower cost. High is the default in Claude Code; Medium is the default in Claude.ai and Cowork. Kieran liked the coding results at all three settings, though our writing tests favored High and Extra-high.","Anthropic estimates costs about 25 percent below Fable 5 for typical API workloads and Claude Code extra usage, with savings approaching 45 percent for extensive autonomous work. Our tests offer evidence of token efficiency: In Every’s Slack assistant, it used less than half as many tokens as Opus 5 with comparable results. We haven’t measured the cost savings against Fable 5.","Anthropic says it is less likely than Mythos 5 to disregard constraints, rationalize its decisions, or game an evaluation. We didn’t run those safety tests, but ordinary instruction-following still had gaps: At Extra-high, Kieran sometimes found it kept working when he interrupted to ask what it was doing.","Standard API rates remain $10 per million input tokens and $50 per million output tokens, matching Fable 5. Reading previously cached input now costs $0.25 per million tokens, a 75 percent reduction. Anthropic estimates overall savings of about 25 percent for typical API workloads and Claude Code extra usage, rising to roughly 45 percent for extensive autonomous work.","At launch, Fable 5.1 will be available in Claude.ai, Claude Code, and Cowork, through Anthropic’s API, and through Amazon Web Services, Google Cloud, and Microsoft Azure.","It handles the same work Fable did, from one-prompt app builds to coding runs that last all day, and it’s easier to work with while it does it. It answers faster, explains what it’s doing in plain language, and changes course when you tell it to instead of arguing.","Dan’s first message to the team about it: “I can actually understand what it’s saying.” The outputs I measured read at a lower grade level than Opus 5 or GPT-5.6 Sol, meaning the text is accessible to more people, with fewer AI tells.","Asked for 1,000 words, it wrote 1,288. Asked for three to six themes, it gave eight. Asked for eight to 12 quotes, it pulled 43, and five of 27 quotes weren’t in the source. At the highest effort setting, it spun up subagents it didn’t need and kept going when Dan asked it to stop and explain.","AI-pilled writer by day, vibe coder by night","For coding, Fable 5.1 does what Fable 5 did, and it’s easier to work with while it does it. Dan moved all of his coding tasks over from Codex. Mike sends all of his new projects to it.","Kieran asked it to rebuild Proof：https://www.proofeditor.ai/ from a single prompt—the same test Fable 5 completed in June. Fable 5.1 also built a working version in one shot, but Kieran found it went deeper, adding useful details he hadn’t specified. He also saw more style and better judgment about what worked. As he put it, “What a time to be alive to get this in one shot.”","It also handled his LFG workflow, where the model plans, writes, reviews, and tests without a person in the loop. By the end of the week, he’d updated the compound engineering plugin：https://github.com/everyinc/compound-engineering-plugin with instructions tailored to it. “It’s the right balance of having an opinion and getting shit done versus pushing back,” he said.","Dan still uses ChatGPT far more for everyday work, but he’s delegating gigantic coding jobs to Fable 5.1 and letting them run. After he got access, Claude Code was making roughly five times as many requests to the model each day.","Mike asked it to move a blog off Webflow. It did it in one prompt. He then asked it to build a version of Stanford’s AI-town simulation：https://arxiv.org/abs/2304.03442, which follows AI characters through their daily routines to see how they form relationships and spread information. In one shot, it created 25 characters with memories and daily routines, who chatted and spread news about a party and a mayoral race happening in the town. “At this point, I’m not even sure what the model can’t do,” Mike said.","Dan ran security-related coding work that Fable had refused in June, when Fable’s safeguards sent those requests to Opus 4.8. Dan noted that refusals on the basis of security risks are “way down”—the model trusts the human’s judgment more on what does or does not constitute a security risk. Kieran also hit fewer false positives during normal engineering work, whereas Fable 5 sometimes mistook routine coding tasks for security work and blocked them. The one refusal Kieran hit: It wouldn’t log in with a test password during an automated testing loop, which he called “a bit extra.”","As for effort levels, Kieran ran the same kinds of tasks at every effort setting and found that Low, Medium, and High were all “super good.” Extra-high “rips” on long runs but hands off too much work to subagents. He’d rather not pick at all: “I just wish they don’t have effort levels and it will do this automatically.” Most of the team settled on High for work with which they stay in the loop.","This is the first Claude model in a year that the writers on our team want to draft with. It writes clear prose in the right order, and it takes an edit without arguing. Still, it needs a fact-checker on long jobs, it hasn’t displaced Opus 5 in our automated editing pipeline：/context-window/benchmarks-don-t-know-your-job, and whether its style beats GPT-5.6 Sol’s is a matter of taste.","On Every’s writing bench, which tasks models with TK editorial tasks, the new model’s best work was the long-form ones, such as writing an introduction from scratch or filling in a missing section of an essay. On the missing passage assignment, which asks the model to define AI slop from Dan’s essay “After Automation,”：/p/after-automation it outscored every model we’ve run, Fable 5 included. Its passages used more of the particulars in the surrounding essay, built the argument so that each paragraph made one point, and stayed faithful to the source material where Fable 5 and Opus 5 tended to infer. Fable 5.1 outputs also carried fewer AI tells than any other model’s, and they read at a seventh-grade level, a grade below Fable 5 and two below Sol.","The X post is the one job where it trailed, landing near the bottom, above only Sonnet 5 while Sol led every Anthropic model. The bench has always split along this line: Anthropic models like to extend an argument, GPT models want to compress it. The new model is the strongest extender we’ve tested and a below-average compressor. Its X posts stack a second and third idea where the brief asked for one.","When you kick the effort level up, the model exercises better judgment about what to leave out. High and xHigh scored best. The gap between medium and high was widest on the paragraph-filling assignment, where the model has to read the surrounding argument and decide what belongs in the gap to make the argument complete, and higher settings wrote shorter: The same introduction ran 805 words at Medium and 657 at xHigh. As with previous models, I settled on High as the best option for drafting.","The same instinct that makes it a good drafter makes it a risky reporter. Given a tight brief and set of sources, it’s faithful. But if you give it long source documents and room to elaborate, it can get creative in the wrong ways: Mike asked it to produce a Vibe Check using eight to 12 exact quotes from the Every team. It produced 43 quotes, including several that were missing from the supplied text.","As an editor it’s fast and timid. Jannik had it edit 20 past Every drafts the way Kate Lee：/@kate_1767, Every’s editor in chief, had edited them. It found Kate’s exact edits about as often as Opus 5 in less than half the time, but threw away about half of what it had found; Opus 5 kept most of its own and Sol nearly all. It can see the edit; it just doesn’t trust itself enough to show you, which is the reverse of its drafting problem. Jannik’s call is that Opus 5 stays the model for that pipeline; Dan’s is that the Fable 5.1 is a little worse and a lot faster.","Give the new model a big consulting assignment and it finishes the whole thing, and on judgment-heavy tasks like slide decks and persona interviews, it beats GPT-5.6 Sol. Give it a brief with a word count, a theme count, or a quote count, and it goes over.","Mike’s EC (executive consulting) Bench covers 12 consulting tasks: dashboards, a training-needs synthesis, a workshop run sheet, a branded slide deck, a roleplayed interview, and others. Sol scored 100 on six of the structured building tasks, then 44 on the blog post and 33 on the roleplayed interview. The new model did the reverse. It scored 88 on persona answers, 93 on the slide deck, and 53 on the roleplay, which Mike still called “basically a fail” but which beat Sol. It lost points where it ignored explicit limits.","Mike asked the model to design three hands-on projects for an executive learning to build with AI, complete with prompts and realistic practice data. One was a dashboard tracking four company acquisitions. The model supplied spreadsheets, status emails, and Slack conversations, including warnings about a project delay that hadn’t yet reached the tracker. In just under 23 minutes, it produced a training pack Mike called “close to perfect.”","Limits are where it loses points. A hotel recommendation with a 1,000-word cap came back at 1,288 words. A training-needs synthesis that called for three to six themes came back with eight. A brief that allowed eight to 12 supporting quotes got 43. A request for markdown got HTML. Opus 5, on the same tasks, stayed inside every limit and timed out twice.","Design is the other weak spot. Mike asked it to build an app that lets people fill out forms by talking to an AI interviewer. The interview worked, but the app had a generic purple-on-black design, large stretches of empty space, and a stray “false” displayed beneath the controls. Fable produced the same purple screen in June. Opus 5 didn’t.","In automated pipelines like Slack assistants designed to execute longform tasks that require tool use, Fable 5.1 does the same work as Opus 5 on about half the tokens and in about 60 percent of the time. Left alone at the highest effort setting, it keeps working, keeps spawning subagents, and doesn’t always stop when you ask. The moral of the story: Set a budget before you start.","Marcus tested both models inside the Every Agent：https://agent.every.to/, our Slack-based AI assistant, using internal checks of its writing and ability to complete tasks with tools. Both ran at Medium effort, with instructions originally tuned for Opus 5. Marcus judged the models’ outputs to be comparable, but Fable 5.1 used less than half as many tokens and responded faster. In Jannik’s editing test, it finished in less than half the time of Opus 5.","Marcus’s caveat: Because it acts fast and spends few tokens, it “can perform worse on heavy multi-tool tasks.” If your pipeline needs a model to chain eight tool calls carefully, Opus 5 is still the safer pick.","Kieran ran long tasks at xHigh and found it “extremely thorough, maybe too much, especially delegating to subagents,” and said that “sometimes [it] does ignore me too.” His xHigh sessions “go for like a day at a time.” When he interrupted one to ask, “Can you explain what you’re doing?” he said it “just ignored me and continued to use a billion subagents.” Mike’s exercise pack ran more than twice his normal time. Kieran put 1.8 billion tokens through it in a single day. It is cheap per step and will take as many steps as you let it, and the effort setting is what decides how many that is.","Fable 5.1 is Fable with less waiting and better manners. It’s faster, writes more clearly, uses fewer tokens per step, argues less, and handles long jobs as well as Fable 5 did. Mike moved his new work to it. Dan moved his coding to it. Katie moved her writing to it, two months after deciding Fable wasn’t for her.","Dan and Kieran give it a gold star for the turnaround and the token efficiency. Mike is holding their gold for a price that lets more people afford Fable-grade work, and Anthropic hadn’t shared a price when we filed this piece. Kieran’s caveat on the comeback story: “Fable never sucked.” Anthropic’s bad months were about Fable being unavailable and two other models missing the mark, while GPT-5.6 came out.","You work with the model in the loop. Writing, editing alongside it, and coding where you read as it goes. High effort is where most of the team landed.","You want Fable-grade results on long jobs without Fable’s wait. Delegated builds, big refactors, and whole-project rebuilds finished for Kieran and Mike at the same level as Fable, faster.","You have Opus 5 agent prompts and a token bill. Marcus got the same pass rate on task completion in the Every Agent at Medium on half the tokens, with a better writing score, without rewriting a prompt.","The brief has hard limits. Word counts, theme counts, quote counts, and output formats all got exceeded in our testing. Opus 5 stayed inside every one.","Quotes have to be right the first time. Five of 27 checkable quotes on one task weren’t in the source. Verify every quotation and every added detail before it leaves your hands.","The task is heavy multi-tool work or a tuned editing pipeline. Marcus and Jannik both found Opus 5 steadier there.","Nobody has set a budget. At xHigh it will take the whole day if you let it.","Whether this is a 4.5 moment—the kind of release that helps a whole new group of people realize what AI makes possible—or just a very good Fable depends on packaging and pricing decisions Anthropic hadn’t shared as of this writing. Either way, the team is using Claude again.","Disclosure: Anthropic provided Every with pre-launch access to Fable 5.1. The company had no input on this review.","Everyone’s a builder now. Every All Access：https://every.to/builder-pack gets you the full membership plus the Builder Pack—$9,000+ in credits for the tools we build with."],"articleImages":[{"sourceUrl":"https://every.to/team/katie.png","alt":"Katie Parrott","afterParagraph":0,"url":"/media/articles/cmtj29bdi03leroh99l1xccw0/1a1a333410debd2f.png"},{"sourceUrl":"https://every.to/team/dan.png","alt":"Dan Shipper","afterParagraph":0,"url":"/media/articles/cmtj29bdi03leroh99l1xccw0/d4cc10b69ebfead1.png"},{"sourceUrl":"https://every.to/team/kieran.png","alt":"Kieran Klaassen","afterParagraph":17,"url":"/media/articles/cmtj29bdi03leroh99l1xccw0/6231788730ead727.png"},{"sourceUrl":"https://every.to/team/mike.png","alt":"Mike Taylor","afterParagraph":17,"url":"/media/articles/cmtj29bdi03leroh99l1xccw0/89381c1cd4db206a.png"}],"mediaStatus":"ok","articleBodyZh":["快速、友好，甚至比其前身更强大","我们称第一个 Fable：/vibe-check/anthropic-mythos-our-fable-vibe-check 为“曲速引擎”，因为它是我们测试过的最强大的编码模型。但它运行缓慢且难以理解——感觉像是一个仅供最资深 AI 用户使用的强力工具。","在我们的测试中，它比 Fable 5 更强大，可以连续运行数天，解决其前身无法解决的编码挑战。但它也快速且友好，更重要的是，它像普通人，呃，像 AI 一样说英语。与原始 Fable 和 Anthropic 最近的 Sonnet 5：/vibe-check/sonnet-5 及 Opus 5：/vibe-check/opus-5 模型不同，Anthropic 回归正轨，创造了一个我们真正享受交流的模型。","哦，还有更多：在我们的测试中，它在执行类似任务时使用的 token 约为 Opus 5 的一半。这应该能在 Opus 预算内完成 Fable 级别的工作。因此，价格也适合所有人。","更有趣的是，“所有人”现在也包括企业。Fable 5.1 提供零数据保留选项，消除了之前阻止大多数大型公司使用它的障碍。","Fable 5.1 是一个罕见的组合：我们使用过的最强大的编码模型，同时也是一个可以推荐给不写代码的人使用的协作者。它应该是大多数知识工作者第一次真切体验 AI 委托工作——以前只能由程序员完成的任务。你可以给它一个任务，比如制作演示文稿，然后去处理其他事情，相信它一两个小时内就能完成出色的成果。","我们已经测试了一周左右，涵盖了编码、写作和知识工作任务。以下是我们零日的 Vibe Check。","Anthropic 表示 Fable 5.1 使其最强大的能力更易用且更便宜。其主要声明如下：","Anthropic 表示该模型可以在长时间运行中追求目标，并对如何解决潜在问题做出更好的决策。Kieran 的经验支持这一点：与 Fable 5 在从零构建 Every 的文档编辑器 Proof 克隆的任务相比，它更深入、添加了他未请求的有用细节，并对什么方法有效表现出更好的判断力。","Anthropic 承诺减少套话、更新更简短，并且对写作指令更加关注。我们也看到了这一点：它的写作中 AI 特征较少，团队发现其解释更易理解。但它仍然经常超出请求的字数。","Anthropic 表示，Low 和 Medium 设置的性能至少可以达到 Fable 5 的水平，且成本明显更低。High 是 Claude Code 中的默认设置；Medium 是 Claude.ai 和 Cowork 中的默认设置。Kieran 对三种设置下的编程结果都很满意，尽管我们的写作测试偏向 High 和 Extra-high。","Anthropic 估算，典型 API 工作负载和 Claude Code 额外使用下，成本比 Fable 5 低约 25%，而对于大量自主工作，节省接近 45%。我们的测试提供了令牌效率的证据：在 Every 的 Slack 助手中，它使用的令牌不到 Opus 5 的一半，但结果相当。我们尚未衡量与 Fable 5 相比的成本节省。","Anthropic 表示，它比 Mythos 5 更不可能忽视约束、为决策寻找理由或操控评估。我们没有做这些安全测试，但普通的指令遵循仍有不足：在 Extra-high 设置下，Kieran 有时发现当他打断它询问正在做什么时，它仍会继续工作。","标准 API 费率仍为每百万输入令牌 10 美元，每百万输出令牌 50 美元，与 Fable 5 相同。读取先前缓存的输入现在收费为每百万令牌 0.25 美元，降低了 75%。Anthropic 估算，对于典型 API 工作负载和 Claude Code 额外使用，总体节省约 25%，对于大量自主工作可提升至约 45%。","在发布时，Fable 5.1 将通过 Anthropic 的 API 在 Claude.ai、Claude Code 和 Cowork 中提供，并通过亚马逊网络服务、谷歌云和微软 Azure 提供。","它处理与 Fable 相同的工作，从单提示应用构建到整天运行的编程任务，并且在工作过程中更容易操作。它回答更快，用简单语言解释正在做的事情，并在你告诉它改变方向时执行，而不会争辩。","Dan 给团队的第一条信息是：“我实际上能理解它在说什么。”我测量的输出读起来比 Opus 5 或 GPT-5.6 Sol 的年级水平低，这意味着文本对更多人来说可以理解，AI 的痕迹更少。","要求写1000字，它写了1288字。要求三到六个主题，它给出了八个。要求八到12条引用，它提取了43条，其中有五条引用不在来源中。在最高努力设置下，它启动了不需要的子代理，并在Dan要求它停止并解释时仍然继续。","白天是AI迷作家，晚上是氛围编程师","在编码方面，Fable 5.1 做到了 Fable 5 所做的事情，而且在执行时更容易操作。Dan 将他所有的编码任务从Codex迁移过来。Mike 将他所有的新项目都交给它处理。","Kieran 要求它从单一提示重建 Proof：https://www.proofeditor.ai/ —— 这是 Fable 5 在六月完成的同一测试。Fable 5.1 也一次性构建了可运行版本，但 Kieran 发现它做得更深入，添加了他未指定的有用细节。他还看到更多风格和对有效方案的更好判断。正如他所说，“能一次性完成这个真是活在好时代。”","它还处理了他的 LFG 工作流程，在该流程中，模型无需人工介入即可进行计划、写作、审查和测试。到周末时，他已经用为模型量身定制的说明更新了复合工程插件：https://github.com/everyinc/compound-engineering-plugin。“它在有自己的观点和完成任务与进行反驳之间取得了恰当平衡，”他说。","Dan仍然更多地使用ChatGPT处理日常工作，但他将巨大的编码任务交给 Fable 5.1 并让其运行。在他获得访问权限后，Claude Code 每天向模型发出的请求大约增加了五倍。","Mike 让它将博客从 Webflow 迁移出去。它一次提示就完成了。接着他要求它构建斯坦福的 AI 城镇模拟版本：https://arxiv.org/abs/2304.03442，该模拟跟随 AI 角色的日常生活，观察他们如何建立关系和传播信息。一次性提示中，它创建了25个带有记忆和日常作息的角色，这些角色交流并传播关于镇上派对和市长选举的消息。“在这一点上，我甚至不确定模型有什么不能做的，”Mike 说道。","丹（Dan）处理了六月份 Fable 拒绝的与安全相关的编码工作，当时 Fable 的防护措施将这些请求发送给了 Opus 4.8。丹指出，以安全风险为由的拒绝“明显减少”——模型在判断什么构成安全风险时更多地信任人的判断。凯兰（Kieran）在常规工程工作中也出现了更少的误报，而 Fable 5 有时会将常规编码任务误判为安全工作并阻止它们。凯兰唯一遇到的拒绝情况是：在自动测试循环中无法使用测试密码登录，他称其为“有点过头”。","关于工作强度，凯兰在每种强度设置下运行了相同类型的任务，并发现低、中、高强度都“超级好”。超高强度在长时间运行时“消耗很猛”，但将太多工作分配给子代理。他宁愿完全不选择：“我只希望它没有强度设置，它会自动完成任务。”团队大部分人对需要保持参与的工作选择了高强度。","这是过去一年中我们团队的作者希望使用的首个 Claude 模型。它的文字顺序清晰，并且能够接受修改而不争论。但在长工作中仍需要事实校对，它尚未取代我们自动化编辑流程中的 Opus 5：/context-window/benchmarks-don-t-know-your-job，至于它的风格是否胜过 GPT-5.6 Sol，则取决于个人喜好。","在 Every 的写作测试台上，该平台安排模型完成 TK 编辑任务，新模型表现最好的任务是长篇任务，例如从零开始写介绍或填补论文中缺失的部分。在缺失段落任务中，该任务要求模型从丹的文章《自动化之后》中定义 AI slop：/p/after-automation，它的得分超过我们运行过的所有模型，包括 Fable 5。它的段落更多地使用了周围文章的细节，使论证清晰，每段表达一个观点，并且忠实于原始材料，而 Fable 5 和 Opus 5 往往会进行推测。Fable 5.1 的输出同样比其他模型的 AI 特征更少，阅读水平为七年级，比 Fable 5 低一个年级，比 Sol 低两个年级。","X 帖子是唯一一个落后的工作，几乎排在最后，仅高于 Sonnet 5，而 Sol 在每个 Anthropic 模型中都领先。基准测试一直沿着这条线分化：Anthropic 模型喜欢扩展论点，GPT 模型则希望压缩它。新模型是我们测试过的最强扩展器，而压缩能力低于平均水平。它的 X 帖子在简短要求一条论点时却堆叠了第二和第三个想法。","当你提高努力水平时，模型在判断如何删减内容上表现更好。High 和 xHigh 得分最高。在段落填充任务中，中等和高之间的差距最大，在这个任务中，模型必须阅读周围的论点并决定插入内容以使论点完整，而高设置下写得更短：同一篇介绍在 Medium 下为 805 字，在 xHigh 下为 657 字。与以往模型一样，我选择 High 作为起草的最佳选项。","同样的直觉让它成为一个优秀的起草者，却让它成为一个有风险的报道者。给它一个紧凑的简报和特定资料时，它很忠诚。但如果你给它长的源文档和扩展的空间，它可能会以错误的方式发挥创造力：Mike 让它用 Every 团队的 8 到 12 个精确引用制作一个 Vibe Check。它生成了 43 个引用，其中包括几条在提供的文本中缺失的。","作为编辑，它速度快但谨慎。Jannik 让它编辑了 20 篇过去 Every 草稿，方式和 Kate Lee（Every 的主编）编辑它们的方式一致。它找到了 Kate 的精确修改次数与 Opus 5 相差不大，但用时不到一半，却丢掉了大约一半找到的修改；Opus 5 保留了大部分自己的修改，Sol 几乎保留全部。它能看见编辑，但没有足够的自信展示给你，这与它起草时的问题正好相反。Jannik 的结论是 Opus 5 仍然适合该流程；Dan 的结论是 Fable 5.1 略差但快得多。","给新模型一个大型咨询任务，它能完成整个任务，在像幻灯片演示和角色访谈这样重判断的任务上，它超过 GPT-5.6 Sol。给它一个带有字数、主题数或引用数的简报，它就会超出限制。","迈克的EC（执行咨询）基准涵盖12项咨询任务：仪表板、培训需求综合、研讨会运行表、品牌幻灯片、角色扮演面试等。Sol在六项结构化构建任务上得了满分100分，然后在博客文章上得了44分，在角色扮演面试上得了33分。新模型则相反。它在角色答案上得了88分，在幻灯片上得了93分，在角色扮演上得了53分，迈克仍然称其为“基本上失败”，但已经超过了Sol。它会在忽略明确限制的地方失分。","迈克要求模型为学习使用AI进行构建的高管设计三个动手项目，包括提示语和真实的练习数据。其中一个是跟踪四次公司收购的仪表板。模型提供了电子表格、状态邮件和Slack对话，包括对尚未到达跟踪器的项目延迟的警告。在不到23分钟的时间里，它生成了一套培训包，迈克称其“接近完美”。","限制是它失分的地方。一个字数上限为1000字的酒店推荐结果为1288字。要求三到六个主题的培训需求综合出了八个。允许八到十二个支持引用的简报出了43个。要求Markdown的结果是HTML。Opus 5在同样任务中，每一项都在限制范围内，且有两次超时。","设计是另一个弱点。迈克要求它构建一个让人们通过与AI面试官对话填写表单的应用。面试功能有效，但应用的设计是通用的黑底紫字，大面积空白，控件下方还显示一个“假”字。Fable在六月也生成了同样的紫色界面。Opus 5没有出现这种情况。","在像Slack助手这样设计用于执行需要工具使用的长任务的自动化流程中，Fable 5.1使用约一半的令牌、约60%的时间完成与Opus 5相同的工作。在最高努力设置下放任不管，它会继续工作，继续生成子代理，并且不总是在你要求时停止。故事的寓意：在开始之前先设定预算。","Marcus 在 Every Agent（https://agent.every.to/，我们的基于 Slack 的 AI 助手）中测试了两种模型，使用内部检查评估它们的写作能力以及使用工具完成任务的能力。两者均设置为中等努力，指令最初为 Opus 5 调整。Marcus 认为这两种模型的输出可比，但 Fable 5.1 使用的 token 不到一半，响应速度更快。在 Jannik 的编辑测试中，它完成的时间不到 Opus 5 的一半。","Marcus 的注意事项：因为它行动迅速且使用的 token 很少，所以“在复杂多工具任务中可能表现较差”。如果你的流程需要模型小心地调用八个工具，Opus 5 仍然是更安全的选择。","Kieran 在 xHigh 设置下运行长任务，发现它“非常彻底，甚至可能过度，尤其是在委派给子代理时”，并表示“有时候[它]也会忽略我。” 他在 xHigh 会话中“每次大约持续一天”。当他中断一个会话问：“你能解释你正在做什么吗？”时，他说它“只是忽略我继续使用无数子代理”。Mike 的演练包运行时间超过他平常的两倍。Kieran 在一天内处理了 18 亿个 token。每个步骤成本低，它会执行你允许的所有步骤，而努力设置决定了执行的步骤数量。","Fable 5.1 是 Fable 的升级版，更少等待，礼貌更佳。它更快，写作更清晰，每步使用的 token 更少，争论更少，并能处理长任务，效果与 Fable 5 相当。Mike 把他的新工作迁移到了它上面。Dan 把他的编程迁移到它上面。Katie 在决定 Fable 不适合她两个月后，把她的写作迁移到它上面。","Dan 和 Kieran 给它在响应速度和 token 效率上打了金星。Mike 持有它们的金星，以一个让更多人负担得起 Fable 级别工作的价格出售，而 Anthropic 在我们撰写本文时尚未公布价格。Kieran 对它回归的评价是：“Fable 从未糟糕。” Anthropic 的不佳时期是由于 Fable 暂时不可用以及其他两种模型未达到标准，而 GPT-5.6 则发布了。","你需要在循环中与模型协作。进行写作、编辑，并在你阅读时编写代码。大努力设置是团队大多数人的选择。","你希望在长时间任务中获得 Fable 水平的结果，却不想等待 Fable 的时间。委派构建、大型重构以及整个项目的重建，对于 Kieran 和 Mike 来说，都能以与 Fable 相同的水平完成，而且更快。","你手上有 Opus 5 代理提示和代币账单。Marcus 在 Every Agent 的 Medium 任务完成率上，用了不到一半的代币获得了相同的通过率，并且写作评分更高，无需重写提示。","简报有严格限制。我们测试中，字数、主题数、引用数和输出格式全都被超出。Opus 5 每一项都严格遵守。","引用必须第一次就正确。在某项任务中可检查的 27 个引用里，有 5 个不在来源中。在引用或新增的细节离开你手中之前，要全部核实。","任务是重型多工具工作或者调优的编辑流程。Marcus 和 Jannik 都发现 Opus 5 在这些方面更稳定。","没人设定预算。在 xHigh 模式下，如果放任不管，可能要花整整一天时间。","这是否是一个 4.5 级时刻——那种发布能让一整批新用户意识到 AI 潜力的时刻——还是仅仅是一个非常好的 Fable，要取决于 Anthropic 目前尚未公开的包装和定价决策。无论如何，团队再次使用了 Claude。","披露：Anthropic 在 Fable 5.1 发布前向 Every 提供了预先访问权限。该公司没有参与本次评测。","现在每个人都是建设者。Every All Access：https://every.to/builder-pack 为你提供完整会员资格加 Builder Pack——即我们构建工具所需的 $9,000+ 代币。"],"translationStatus":"translated","bodyOrigin":"source-page","editorial":{"summary":"Every 在约一周的测试后发布 Fable 5.1 体验评测，称其在编程、写作和知识工作任务中比 Fable 5 更强，同时更快、更易交流；文章还称，相似任务下其令牌用量约为 Opus 5 的一半。","background":"Every 此前将初代 Fable 称为其测试过最强的编程模型，但认为该模型速度慢且难以理解。本次文章称 Fable 5.1 提供零数据保留选项，并表示 Anthropic 的主要主张是让模型能力更易用、成本更低。","viewpoint":"Aioga 判断：这篇文章的核心价值在于提供早期实际使用感受，并将能力、交互体验、令牌用量和数据保留并列考察；但其结论来自 Every 的短期测试，适用范围仍需更多材料验证。","implications":"可能影响：若令牌用量、长任务执行和零数据保留等表现得到进一步验证，Fable 5.1 可能降低部分使用门槛；不过单篇体验评测不足以证明其在不同任务和环境中的普遍表现。","nextStep":"后续观察：需要核对 Anthropic 对 Fable 5.1 的完整说明，并关注独立测试对编程、写作、知识工作、令牌消耗及零数据保留选项的验证结果，同时区分厂商主张与 Every 的体验结论。","evidenceRefs":["title","summary","articleBody","source"],"status":"published","aiGenerated":true,"autoApproved":true,"generatedBy":"aioga-editorial:gpt-5.6-sol","reviewedBy":"aioga-editorial-review:gpt-5.6-sol","generatedAt":"2026-09-01T19:46:18.467Z","sourceHash":"204d9e13a825dc28","review":{"approved":true,"groundedness":95,"clarity":92,"duplicationRisk":12,"blockingIssues":[],"notes":["“更易交流”是对原文“fast and friendly”“speaks English like a normal person”的概括，基本准确；如需更严格，可改为“更自然、更易理解”。","“Anthropic 的主要主张”属于来源中的明确表述，但候选内容已通过上下文区分厂商主张与 Every 的测试结论，处理恰当。","候选内容中的影响判断和后续观察均使用条件性表述，没有将体验评测结论扩展为普遍事实。"]},"validation":{"passed":true,"mode":"ai-auto","revisions":0,"checks":["schema","length","source-attribution","editorial-labels","inference-boundary","low-source-overlap","no-html","independent-ai-review"]}},"tags":["行业动态","Every：最新文章（网页）"],"translations":{"zh-CN":{"title":"Fable 5.1 体验评测：Anthropic Is So Back（again）","summary":"Every 发布 Fable 5.1 的体验评测文章，标题称 Anthropic Is So Back（Again）。正文未提供有效文本，具体评测内容以原文为准。","category":"行业动态","source":"Every：最新文章（网页）","aggregationSource":"Every：最新文章（网页）","pageTitle":"Fable 5.1 体验评测：Anthropic Is So Back（again） - Aioga AI资讯","description":"Every 发布 Fable 5.1 的体验评测文章，标题称 Anthropic Is So Back（Again）。正文未提供有效文本，具体评测内容以原文为准。","url":"https://www.aioga.com/news/cmtj29bdi03leroh99l1xccw0/","articleBody":["快速、友好，甚至比其前身更强大","我们称第一个 Fable：/vibe-check/anthropic-mythos-our-fable-vibe-check 为“曲速引擎”，因为它是我们测试过的最强大的编码模型。但它运行缓慢且难以理解——感觉像是一个仅供最资深 AI 用户使用的强力工具。","在我们的测试中，它比 Fable 5 更强大，可以连续运行数天，解决其前身无法解决的编码挑战。但它也快速且友好，更重要的是，它像普通人，呃，像 AI 一样说英语。与原始 Fable 和 Anthropic 最近的 Sonnet 5：/vibe-check/sonnet-5 及 Opus 5：/vibe-check/opus-5 模型不同，Anthropic 回归正轨，创造了一个我们真正享受交流的模型。","哦，还有更多：在我们的测试中，它在执行类似任务时使用的 token 约为 Opus 5 的一半。这应该能在 Opus 预算内完成 Fable 级别的工作。因此，价格也适合所有人。","更有趣的是，“所有人”现在也包括企业。Fable 5.1 提供零数据保留选项，消除了之前阻止大多数大型公司使用它的障碍。","Fable 5.1 是一个罕见的组合：我们使用过的最强大的编码模型，同时也是一个可以推荐给不写代码的人使用的协作者。它应该是大多数知识工作者第一次真切体验 AI 委托工作——以前只能由程序员完成的任务。你可以给它一个任务，比如制作演示文稿，然后去处理其他事情，相信它一两个小时内就能完成出色的成果。","我们已经测试了一周左右，涵盖了编码、写作和知识工作任务。以下是我们零日的 Vibe Check。","Anthropic 表示 Fable 5.1 使其最强大的能力更易用且更便宜。其主要声明如下：","Anthropic 表示该模型可以在长时间运行中追求目标，并对如何解决潜在问题做出更好的决策。Kieran 的经验支持这一点：与 Fable 5 在从零构建 Every 的文档编辑器 Proof 克隆的任务相比，它更深入、添加了他未请求的有用细节，并对什么方法有效表现出更好的判断力。","Anthropic 承诺减少套话、更新更简短，并且对写作指令更加关注。我们也看到了这一点：它的写作中 AI 特征较少，团队发现其解释更易理解。但它仍然经常超出请求的字数。","Anthropic 表示，Low 和 Medium 设置的性能至少可以达到 Fable 5 的水平，且成本明显更低。High 是 Claude Code 中的默认设置；Medium 是 Claude.ai 和 Cowork 中的默认设置。Kieran 对三种设置下的编程结果都很满意，尽管我们的写作测试偏向 High 和 Extra-high。","Anthropic 估算，典型 API 工作负载和 Claude Code 额外使用下，成本比 Fable 5 低约 25%，而对于大量自主工作，节省接近 45%。我们的测试提供了令牌效率的证据：在 Every 的 Slack 助手中，它使用的令牌不到 Opus 5 的一半，但结果相当。我们尚未衡量与 Fable 5 相比的成本节省。","Anthropic 表示，它比 Mythos 5 更不可能忽视约束、为决策寻找理由或操控评估。我们没有做这些安全测试，但普通的指令遵循仍有不足：在 Extra-high 设置下，Kieran 有时发现当他打断它询问正在做什么时，它仍会继续工作。","标准 API 费率仍为每百万输入令牌 10 美元，每百万输出令牌 50 美元，与 Fable 5 相同。读取先前缓存的输入现在收费为每百万令牌 0.25 美元，降低了 75%。Anthropic 估算，对于典型 API 工作负载和 Claude Code 额外使用，总体节省约 25%，对于大量自主工作可提升至约 45%。","在发布时，Fable 5.1 将通过 Anthropic 的 API 在 Claude.ai、Claude Code 和 Cowork 中提供，并通过亚马逊网络服务、谷歌云和微软 Azure 提供。","它处理与 Fable 相同的工作，从单提示应用构建到整天运行的编程任务，并且在工作过程中更容易操作。它回答更快，用简单语言解释正在做的事情，并在你告诉它改变方向时执行，而不会争辩。","Dan 给团队的第一条信息是：“我实际上能理解它在说什么。”我测量的输出读起来比 Opus 5 或 GPT-5.6 Sol 的年级水平低，这意味着文本对更多人来说可以理解，AI 的痕迹更少。","要求写1000字，它写了1288字。要求三到六个主题，它给出了八个。要求八到12条引用，它提取了43条，其中有五条引用不在来源中。在最高努力设置下，它启动了不需要的子代理，并在Dan要求它停止并解释时仍然继续。","白天是AI迷作家，晚上是氛围编程师","在编码方面，Fable 5.1 做到了 Fable 5 所做的事情，而且在执行时更容易操作。Dan 将他所有的编码任务从Codex迁移过来。Mike 将他所有的新项目都交给它处理。","Kieran 要求它从单一提示重建 Proof：https://www.proofeditor.ai/ —— 这是 Fable 5 在六月完成的同一测试。Fable 5.1 也一次性构建了可运行版本，但 Kieran 发现它做得更深入，添加了他未指定的有用细节。他还看到更多风格和对有效方案的更好判断。正如他所说，“能一次性完成这个真是活在好时代。”","它还处理了他的 LFG 工作流程，在该流程中，模型无需人工介入即可进行计划、写作、审查和测试。到周末时，他已经用为模型量身定制的说明更新了复合工程插件：https://github.com/everyinc/compound-engineering-plugin。“它在有自己的观点和完成任务与进行反驳之间取得了恰当平衡，”他说。","Dan仍然更多地使用ChatGPT处理日常工作，但他将巨大的编码任务交给 Fable 5.1 并让其运行。在他获得访问权限后，Claude Code 每天向模型发出的请求大约增加了五倍。","Mike 让它将博客从 Webflow 迁移出去。它一次提示就完成了。接着他要求它构建斯坦福的 AI 城镇模拟版本：https://arxiv.org/abs/2304.03442，该模拟跟随 AI 角色的日常生活，观察他们如何建立关系和传播信息。一次性提示中，它创建了25个带有记忆和日常作息的角色，这些角色交流并传播关于镇上派对和市长选举的消息。“在这一点上，我甚至不确定模型有什么不能做的，”Mike 说道。","丹（Dan）处理了六月份 Fable 拒绝的与安全相关的编码工作，当时 Fable 的防护措施将这些请求发送给了 Opus 4.8。丹指出，以安全风险为由的拒绝“明显减少”——模型在判断什么构成安全风险时更多地信任人的判断。凯兰（Kieran）在常规工程工作中也出现了更少的误报，而 Fable 5 有时会将常规编码任务误判为安全工作并阻止它们。凯兰唯一遇到的拒绝情况是：在自动测试循环中无法使用测试密码登录，他称其为“有点过头”。","关于工作强度，凯兰在每种强度设置下运行了相同类型的任务，并发现低、中、高强度都“超级好”。超高强度在长时间运行时“消耗很猛”，但将太多工作分配给子代理。他宁愿完全不选择：“我只希望它没有强度设置，它会自动完成任务。”团队大部分人对需要保持参与的工作选择了高强度。","这是过去一年中我们团队的作者希望使用的首个 Claude 模型。它的文字顺序清晰，并且能够接受修改而不争论。但在长工作中仍需要事实校对，它尚未取代我们自动化编辑流程中的 Opus 5：/context-window/benchmarks-don-t-know-your-job，至于它的风格是否胜过 GPT-5.6 Sol，则取决于个人喜好。","在 Every 的写作测试台上，该平台安排模型完成 TK 编辑任务，新模型表现最好的任务是长篇任务，例如从零开始写介绍或填补论文中缺失的部分。在缺失段落任务中，该任务要求模型从丹的文章《自动化之后》中定义 AI slop：/p/after-automation，它的得分超过我们运行过的所有模型，包括 Fable 5。它的段落更多地使用了周围文章的细节，使论证清晰，每段表达一个观点，并且忠实于原始材料，而 Fable 5 和 Opus 5 往往会进行推测。Fable 5.1 的输出同样比其他模型的 AI 特征更少，阅读水平为七年级，比 Fable 5 低一个年级，比 Sol 低两个年级。","X 帖子是唯一一个落后的工作，几乎排在最后，仅高于 Sonnet 5，而 Sol 在每个 Anthropic 模型中都领先。基准测试一直沿着这条线分化：Anthropic 模型喜欢扩展论点，GPT 模型则希望压缩它。新模型是我们测试过的最强扩展器，而压缩能力低于平均水平。它的 X 帖子在简短要求一条论点时却堆叠了第二和第三个想法。","当你提高努力水平时，模型在判断如何删减内容上表现更好。High 和 xHigh 得分最高。在段落填充任务中，中等和高之间的差距最大，在这个任务中，模型必须阅读周围的论点并决定插入内容以使论点完整，而高设置下写得更短：同一篇介绍在 Medium 下为 805 字，在 xHigh 下为 657 字。与以往模型一样，我选择 High 作为起草的最佳选项。","同样的直觉让它成为一个优秀的起草者，却让它成为一个有风险的报道者。给它一个紧凑的简报和特定资料时，它很忠诚。但如果你给它长的源文档和扩展的空间，它可能会以错误的方式发挥创造力：Mike 让它用 Every 团队的 8 到 12 个精确引用制作一个 Vibe Check。它生成了 43 个引用，其中包括几条在提供的文本中缺失的。","作为编辑，它速度快但谨慎。Jannik 让它编辑了 20 篇过去 Every 草稿，方式和 Kate Lee（Every 的主编）编辑它们的方式一致。它找到了 Kate 的精确修改次数与 Opus 5 相差不大，但用时不到一半，却丢掉了大约一半找到的修改；Opus 5 保留了大部分自己的修改，Sol 几乎保留全部。它能看见编辑，但没有足够的自信展示给你，这与它起草时的问题正好相反。Jannik 的结论是 Opus 5 仍然适合该流程；Dan 的结论是 Fable 5.1 略差但快得多。","给新模型一个大型咨询任务，它能完成整个任务，在像幻灯片演示和角色访谈这样重判断的任务上，它超过 GPT-5.6 Sol。给它一个带有字数、主题数或引用数的简报，它就会超出限制。","迈克的EC（执行咨询）基准涵盖12项咨询任务：仪表板、培训需求综合、研讨会运行表、品牌幻灯片、角色扮演面试等。Sol在六项结构化构建任务上得了满分100分，然后在博客文章上得了44分，在角色扮演面试上得了33分。新模型则相反。它在角色答案上得了88分，在幻灯片上得了93分，在角色扮演上得了53分，迈克仍然称其为“基本上失败”，但已经超过了Sol。它会在忽略明确限制的地方失分。","迈克要求模型为学习使用AI进行构建的高管设计三个动手项目，包括提示语和真实的练习数据。其中一个是跟踪四次公司收购的仪表板。模型提供了电子表格、状态邮件和Slack对话，包括对尚未到达跟踪器的项目延迟的警告。在不到23分钟的时间里，它生成了一套培训包，迈克称其“接近完美”。","限制是它失分的地方。一个字数上限为1000字的酒店推荐结果为1288字。要求三到六个主题的培训需求综合出了八个。允许八到十二个支持引用的简报出了43个。要求Markdown的结果是HTML。Opus 5在同样任务中，每一项都在限制范围内，且有两次超时。","设计是另一个弱点。迈克要求它构建一个让人们通过与AI面试官对话填写表单的应用。面试功能有效，但应用的设计是通用的黑底紫字，大面积空白，控件下方还显示一个“假”字。Fable在六月也生成了同样的紫色界面。Opus 5没有出现这种情况。","在像Slack助手这样设计用于执行需要工具使用的长任务的自动化流程中，Fable 5.1使用约一半的令牌、约60%的时间完成与Opus 5相同的工作。在最高努力设置下放任不管，它会继续工作，继续生成子代理，并且不总是在你要求时停止。故事的寓意：在开始之前先设定预算。","Marcus 在 Every Agent（https://agent.every.to/，我们的基于 Slack 的 AI 助手）中测试了两种模型，使用内部检查评估它们的写作能力以及使用工具完成任务的能力。两者均设置为中等努力，指令最初为 Opus 5 调整。Marcus 认为这两种模型的输出可比，但 Fable 5.1 使用的 token 不到一半，响应速度更快。在 Jannik 的编辑测试中，它完成的时间不到 Opus 5 的一半。","Marcus 的注意事项：因为它行动迅速且使用的 token 很少，所以“在复杂多工具任务中可能表现较差”。如果你的流程需要模型小心地调用八个工具，Opus 5 仍然是更安全的选择。","Kieran 在 xHigh 设置下运行长任务，发现它“非常彻底，甚至可能过度，尤其是在委派给子代理时”，并表示“有时候[它]也会忽略我。” 他在 xHigh 会话中“每次大约持续一天”。当他中断一个会话问：“你能解释你正在做什么吗？”时，他说它“只是忽略我继续使用无数子代理”。Mike 的演练包运行时间超过他平常的两倍。Kieran 在一天内处理了 18 亿个 token。每个步骤成本低，它会执行你允许的所有步骤，而努力设置决定了执行的步骤数量。","Fable 5.1 是 Fable 的升级版，更少等待，礼貌更佳。它更快，写作更清晰，每步使用的 token 更少，争论更少，并能处理长任务，效果与 Fable 5 相当。Mike 把他的新工作迁移到了它上面。Dan 把他的编程迁移到它上面。Katie 在决定 Fable 不适合她两个月后，把她的写作迁移到它上面。","Dan 和 Kieran 给它在响应速度和 token 效率上打了金星。Mike 持有它们的金星，以一个让更多人负担得起 Fable 级别工作的价格出售，而 Anthropic 在我们撰写本文时尚未公布价格。Kieran 对它回归的评价是：“Fable 从未糟糕。” Anthropic 的不佳时期是由于 Fable 暂时不可用以及其他两种模型未达到标准，而 GPT-5.6 则发布了。","你需要在循环中与模型协作。进行写作、编辑，并在你阅读时编写代码。大努力设置是团队大多数人的选择。","你希望在长时间任务中获得 Fable 水平的结果，却不想等待 Fable 的时间。委派构建、大型重构以及整个项目的重建，对于 Kieran 和 Mike 来说，都能以与 Fable 相同的水平完成，而且更快。","你手上有 Opus 5 代理提示和代币账单。Marcus 在 Every Agent 的 Medium 任务完成率上，用了不到一半的代币获得了相同的通过率，并且写作评分更高，无需重写提示。","简报有严格限制。我们测试中，字数、主题数、引用数和输出格式全都被超出。Opus 5 每一项都严格遵守。","引用必须第一次就正确。在某项任务中可检查的 27 个引用里，有 5 个不在来源中。在引用或新增的细节离开你手中之前，要全部核实。","任务是重型多工具工作或者调优的编辑流程。Marcus 和 Jannik 都发现 Opus 5 在这些方面更稳定。","没人设定预算。在 xHigh 模式下，如果放任不管，可能要花整整一天时间。","这是否是一个 4.5 级时刻——那种发布能让一整批新用户意识到 AI 潜力的时刻——还是仅仅是一个非常好的 Fable，要取决于 Anthropic 目前尚未公开的包装和定价决策。无论如何，团队再次使用了 Claude。","披露：Anthropic 在 Fable 5.1 发布前向 Every 提供了预先访问权限。该公司没有参与本次评测。","现在每个人都是建设者。Every All Access：https://every.to/builder-pack 为你提供完整会员资格加 Builder Pack——即我们构建工具所需的 $9,000+ 代币。"]},"en":{"title":"Fable 5.1 Experience Review: Anthropic Is So Back (again)","summary":"Every published a review article about Fable 5.1, titled 'Anthropic Is So Back (Again)'. The main text does not provide any valid text; the actual review content shall prevail.","category":"Industry","source":"Every：最新文章（网页）","aggregationSource":"Every：最新文章（网页）","pageTitle":"Fable 5.1 Experience Review: Anthropic Is So Back (again) - Aioga AI News","description":"Every published a review article about Fable 5.1, titled 'Anthropic Is So Back (Again)'. The main text does not provide any valid text; the actual review content shall prevail.","url":"https://www.aioga.com/en/news/cmtj29bdi03leroh99l1xccw0/","contentTranslated":true,"sourceHash":"44803b036fce9f88","translatedAt":"2026-09-01T19:41:57.056Z"},"ja":{"title":"ファーブル メーデー体験レビュー:アントロピク・イッソ・バーク(アルゲン)","summary":"エヴェリはFabre 5.1に「Antropique Isso Bak(アルガン)」という経験レビュー記事を発表しました。 本文には有効なテキストは記載されていません。具体的な評価内容については原文をご参照ください。","category":"業界動向","source":"Every：最新文章（网页）","aggregationSource":"Every：最新文章（网页）","pageTitle":"ファーブル メーデー体験レビュー:アントロピク・イッソ・バーク(アルゲン) - Aioga AIニュース","description":"エヴェリはFabre 5.1に「Antropique Isso Bak(アルガン)」という経験レビュー記事を発表しました。 本文には有効なテキストは記載されていません。具体的な評価内容については原文をご参照ください。","url":"https://www.aioga.com/ja/news/cmtj29bdi03leroh99l1xccw0/","contentTranslated":true,"sourceHash":"44803b036fce9f88","translatedAt":"2026-09-01T19:41:57.465Z"},"ko":{"title":"파브르 메이데이 체험 리뷰: 안트로피크 이소 바크 (아르젠)","summary":"에베리는 Fabre 5.1에 'Antropique Isso Bak (Argan)'이라는 경험 리뷰 논문을 발표했습니다. 본문에는 유효한 텍스트가 제공되지 않습니다. 구체적인 평가 내용은 원본을 참조해 주시기 바랍니다.","category":"업계 동향","source":"Every：最新文章（网页）","aggregationSource":"Every：最新文章（网页）","pageTitle":"파브르 메이데이 체험 리뷰: 안트로피크 이소 바크 (아르젠) - Aioga AI 뉴스","description":"에베리는 Fabre 5.1에 'Antropique Isso Bak (Argan)'이라는 경험 리뷰 논문을 발표했습니다. 본문에는 유효한 텍스트가 제공되지 않습니다. 구체적인 평가 내용은 원본을 참조해 주시기 바랍니다.","url":"https://www.aioga.com/ko/news/cmtj29bdi03leroh99l1xccw0/","contentTranslated":true,"sourceHash":"44803b036fce9f88","translatedAt":"2026-09-01T19:42:06.256Z"},"es":{"title":"Reseña de la experiencia de Fabre May Day: Antropique Isso Bark (Argen)","summary":"Everri publicó un artículo de revisión de experiencias para Fabre 5.1, titulado Antropique Isso Bak (Argan). No se proporciona ningún texto válido en el texto principal; por favor, consulte el texto original para el contenido específico de la evaluación.","category":"Industria","source":"Every：最新文章（网页）","aggregationSource":"Every：最新文章（网页）","pageTitle":"Reseña de la experiencia de Fabre May Day: Antropique Isso Bark (Argen) - Aioga Noticias de IA","description":"Everri publicó un artículo de revisión de experiencias para Fabre 5.1, titulado Antropique Isso Bak (Argan). No se proporciona ningún texto válido en el texto principal; por favor,...","url":"https://www.aioga.com/es/news/cmtj29bdi03leroh99l1xccw0/","contentTranslated":true,"sourceHash":"44803b036fce9f88","translatedAt":"2026-09-01T19:42:07.021Z"},"fr":{"title":"Critique de l’expérience Fabre May Day : Antropique Isso Bark (Argen)","summary":"Everri a publié un article de revue d’expérience pour Fabre 5.1, intitulé Antropique Isso Bak (Argan). Aucun texte valide n’est fourni dans le texte principal ; veuillez consulter le texte original pour le contenu spécifique de l’évaluation.","category":"Industrie","source":"Every：最新文章（网页）","aggregationSource":"Every：最新文章（网页）","pageTitle":"Critique de l’expérience Fabre May Day : Antropique Isso Bark (Argen) - Aioga Actualités IA","description":"Everri a publié un article de revue d’expérience pour Fabre 5.1, intitulé Antropique Isso Bak (Argan). Aucun texte valide n’est fourni dans le texte principal ; veuillez consulter...","url":"https://www.aioga.com/fr/news/cmtj29bdi03leroh99l1xccw0/","contentTranslated":true,"sourceHash":"44803b036fce9f88","translatedAt":"2026-09-01T19:42:14.946Z"},"de":{"title":"Fabre May Day Experience Bewertung: Antropique Isso Rinde (Argen)","summary":"Everri veröffentlichte einen Erfahrungsartikel für Fabre 5.1 mit dem Titel Antropique Isso Bak (Argan). Im Haupttext ist kein gültiger Text enthalten; bitte lesen Sie den Originaltext für den spezifischen Bewertungsinhalt.","category":"行业动态","source":"Every：最新文章（网页）","aggregationSource":"Every：最新文章（网页）","pageTitle":"Fabre May Day Experience Bewertung: Antropique Isso Rinde (Argen) - Aioga KI-News","description":"Everri veröffentlichte einen Erfahrungsartikel für Fabre 5.1 mit dem Titel Antropique Isso Bak (Argan). Im Haupttext ist kein gültiger Text enthalten; bitte lesen Sie den Originalt...","url":"https://www.aioga.com/de/news/cmtj29bdi03leroh99l1xccw0/","contentTranslated":true,"sourceHash":"44803b036fce9f88","translatedAt":"2026-09-01T19:42:15.163Z"},"pt-BR":{"title":"Análise da Experiência do Dia do Trabalhador de Maio: Antropique Isso Bark (Argen)","summary":"Everri publicou um artigo de revisão de experiências para o Fabre 5.1, intitulado Antropique Isso Bak (Argan). Nenhum texto válido é fornecido no texto principal; por favor, consulte o texto original para o conteúdo específico da avaliação.","category":"行业动态","source":"Every：最新文章（网页）","aggregationSource":"Every：最新文章（网页）","pageTitle":"Análise da Experiência do Dia do Trabalhador de Maio: Antropique Isso Bark (Argen) - Aioga Notícias de IA","description":"Everri publicou um artigo de revisão de experiências para o Fabre 5.1, intitulado Antropique Isso Bak (Argan). Nenhum texto válido é fornecido no texto principal; por favor, consul...","url":"https://www.aioga.com/pt-BR/news/cmtj29bdi03leroh99l1xccw0/","contentTranslated":true,"sourceHash":"44803b036fce9f88","translatedAt":"2026-09-01T19:42:23.729Z"},"ru":{"title":"Обзор Fabre May Day Experience: кора Antropique Isso (Argen)","summary":"Everri опубликовала обзорную статью для Fabre 5.1 под названием Antropique Isso Bak (Argan). В основном тексте не приводится действительный текст; пожалуйста, обратитесь к оригинальному тексту для конкретного содержания оценки.","category":"行业动态","source":"Every：最新文章（网页）","aggregationSource":"Every：最新文章（网页）","pageTitle":"Обзор Fabre May Day Experience: кора Antropique Isso (Argen) - Aioga Новости ИИ","description":"Everri опубликовала обзорную статью для Fabre 5.1 под названием Antropique Isso Bak (Argan). В основном тексте не приводится действительный текст; пожалуйста, обратитесь к оригинал...","url":"https://www.aioga.com/ru/news/cmtj29bdi03leroh99l1xccw0/","contentTranslated":true,"sourceHash":"44803b036fce9f88","translatedAt":"2026-09-01T19:42:23.934Z"},"ar":{"title":"مراجعة تجربة فابر ماي داي: أنتروبيك إيسو بارك (أرجين)","summary":"نشرت مجلة إيفري مقالا مراجعة تجارب لمجلة فابر 5.1 بعنوان Antropique Isso Bak (أرغان). لا يوجد نص صالح في النص الرئيسي؛ يرجى الرجوع إلى النص الأصلي لمحتوى التقييم المحدد.","category":"行业动态","source":"Every：最新文章（网页）","aggregationSource":"Every：最新文章（网页）","pageTitle":"مراجعة تجربة فابر ماي داي: أنتروبيك إيسو بارك (أرجين) - Aioga أخبار الذكاء الاصطناعي","description":"نشرت مجلة إيفري مقالا مراجعة تجارب لمجلة فابر 5.1 بعنوان Antropique Isso Bak (أرغان). لا يوجد نص صالح في النص الرئيسي؛ يرجى الرجوع إلى النص الأصلي لمحتوى التقييم المحدد.","url":"https://www.aioga.com/ar/news/cmtj29bdi03leroh99l1xccw0/","contentTranslated":true,"sourceHash":"44803b036fce9f88","translatedAt":"2026-09-01T19:42:31.823Z"},"hi":{"title":"फैबरे मई डे अनुभव की समीक्षा: एंट्रोपिक इस्सो बार्क (अर्जेन)","summary":"एवरी ने फैब्रे 5.1 के लिए एक अनुभव समीक्षा लेख प्रकाशित किया, जिसका शीर्षक एंट्रोपिक इस्सो बाक (आर्गन) था। मुख्य पाठ में कोई मान्य पाठ प्रदान नहीं किया गया है; कृपया विशिष्ट मूल्यांकन सामग्री के लिए मूल पाठ देखें।","category":"行业动态","source":"Every：最新文章（网页）","aggregationSource":"Every：最新文章（网页）","pageTitle":"फैबरे मई डे अनुभव की समीक्षा: एंट्रोपिक इस्सो बार्क (अर्जेन) - Aioga AI समाचार","description":"एवरी ने फैब्रे 5.1 के लिए एक अनुभव समीक्षा लेख प्रकाशित किया, जिसका शीर्षक एंट्रोपिक इस्सो बाक (आर्गन) था। मुख्य पाठ में कोई मान्य पाठ प्रदान नहीं किया गया है; कृपया विशिष्ट मूल्या...","url":"https://www.aioga.com/hi/news/cmtj29bdi03leroh99l1xccw0/","contentTranslated":true,"sourceHash":"44803b036fce9f88","translatedAt":"2026-09-01T19:42:33.183Z"},"it":{"title":"Recensione dell'esperienza Fabre May Day: Antropique Isso Bark (Argen)","summary":"Everri ha pubblicato un articolo di revisione dell'esperienza per Fabre 5.1, intitolato Antropique Isso Bak (Argan). Non è fornito testo valido nel testo principale; si prega di fare riferimento al testo originale per il contenuto specifico della valutazione.","category":"行业动态","source":"Every：最新文章（网页）","aggregationSource":"Every：最新文章（网页）","pageTitle":"Recensione dell'esperienza Fabre May Day: Antropique Isso Bark (Argen) - Aioga Notizie IA","description":"Everri ha pubblicato un articolo di revisione dell'esperienza per Fabre 5.1, intitolato Antropique Isso Bak (Argan). Non è fornito testo valido nel testo principale; si prega di fa...","url":"https://www.aioga.com/it/news/cmtj29bdi03leroh99l1xccw0/","contentTranslated":true,"sourceHash":"44803b036fce9f88","translatedAt":"2026-09-01T19:42:41.500Z"},"nl":{"title":"Fabre May Day Experience Recensie: Antropique Isso Schors (Argen)","summary":"Everri publiceerde een ervaringsoverzichtsartikel voor Fabre 5.1, getiteld Antropique Isso Bak (Argan). In de hoofdtekst wordt geen geldige tekst verstrekt; raadpleeg de oorspronkelijke tekst voor de specifieke evaluatie-inhoud.","category":"行业动态","source":"Every：最新文章（网页）","aggregationSource":"Every：最新文章（网页）","pageTitle":"Fabre May Day Experience Recensie: Antropique Isso Schors (Argen) - Aioga AI-nieuws","description":"Everri publiceerde een ervaringsoverzichtsartikel voor Fabre 5.1, getiteld Antropique Isso Bak (Argan). In de hoofdtekst wordt geen geldige tekst verstrekt; raadpleeg de oorspronke...","url":"https://www.aioga.com/nl/news/cmtj29bdi03leroh99l1xccw0/","contentTranslated":true,"sourceHash":"44803b036fce9f88","translatedAt":"2026-09-01T19:42:43.581Z"},"tr":{"title":"Fabre Mayıs Günü Deneyimi İncelemesi: Antropique Isso Bark (Argen)","summary":"Everri, Fabre 5.1 için Antropique Isso Bak (Argan) başlıklı bir deneyim inceleme makalesi yayımladı. Ana metinde geçerli bir metin sağlanmamıştır; özel değerlendirme içeriği için lütfen orijinal metne bakınız.","category":"行业动态","source":"Every：最新文章（网页）","aggregationSource":"Every：最新文章（网页）","pageTitle":"Fabre Mayıs Günü Deneyimi İncelemesi: Antropique Isso Bark (Argen) - Aioga AI Haberleri","description":"Everri, Fabre 5.1 için Antropique Isso Bak (Argan) başlıklı bir deneyim inceleme makalesi yayımladı. Ana metinde geçerli bir metin sağlanmamıştır; özel değerlendirme içeriği için l...","url":"https://www.aioga.com/tr/news/cmtj29bdi03leroh99l1xccw0/","contentTranslated":true,"sourceHash":"44803b036fce9f88","translatedAt":"2026-09-01T19:42:51.964Z"},"vi":{"title":"Đánh giá trải nghiệm Fabre May Day: Vỏ cây Antropique Isso (Argen)","summary":"Everri đã công bố một bài tổng quan kinh nghiệm cho Fabre 5.1, có tựa đề Antropique Isso Bak (Argan). Không có văn bản hợp lệ nào được cung cấp trong văn bản chính; vui lòng tham khảo văn bản gốc để biết nội dung đánh giá cụ thể.","category":"行业动态","source":"Every：最新文章（网页）","aggregationSource":"Every：最新文章（网页）","pageTitle":"Đánh giá trải nghiệm Fabre May Day: Vỏ cây Antropique Isso (Argen) - Tin tức AI Aioga","description":"Everri đã công bố một bài tổng quan kinh nghiệm cho Fabre 5.1, có tựa đề Antropique Isso Bak (Argan). Không có văn bản hợp lệ nào được cung cấp trong văn bản chính; vui lòng tham k...","url":"https://www.aioga.com/vi/news/cmtj29bdi03leroh99l1xccw0/","contentTranslated":true,"sourceHash":"44803b036fce9f88","translatedAt":"2026-09-01T19:42:52.706Z"},"id":{"title":"Ulasan Pengalaman Fabre May Day: Antropique Isso Bark (Argen)","summary":"Everri menerbitkan artikel ulasan pengalaman untuk Fabre 5.1, berjudul Antropique Isso Bak (Argan). Tidak ada teks yang valid yang disediakan dalam teks utama; silakan merujuk pada teks asli untuk isi evaluasi spesifik.","category":"行业动态","source":"Every：最新文章（网页）","aggregationSource":"Every：最新文章（网页）","pageTitle":"Ulasan Pengalaman Fabre May Day: Antropique Isso Bark (Argen) - Berita AI Aioga","description":"Everri menerbitkan artikel ulasan pengalaman untuk Fabre 5.1, berjudul Antropique Isso Bak (Argan). Tidak ada teks yang valid yang disediakan dalam teks utama; silakan merujuk pada...","url":"https://www.aioga.com/id/news/cmtj29bdi03leroh99l1xccw0/","contentTranslated":true,"sourceHash":"44803b036fce9f88","translatedAt":"2026-09-01T19:43:01.550Z"},"th":{"title":"รีวิวประสบการณ์วันเมย์เดย์ของ Fabre: เปลือกไม้ Antropique Isso (Argen)","summary":"Everri ได้ตีพิมพ์บทความทบทวนประสบการณ์สําหรับ Fabre 5.1 ชื่อว่า Antropique Isso Bak (Argan) ไม่มีข้อความที่ถูกต้องในข้อความหลัก กรุณาอ้างอิงข้อความต้นฉบับสําหรับเนื้อหาการประเมินเฉพาะ","category":"行业动态","source":"Every：最新文章（网页）","aggregationSource":"Every：最新文章（网页）","pageTitle":"รีวิวประสบการณ์วันเมย์เดย์ของ Fabre: เปลือกไม้ Antropique Isso (Argen) - ข่าว AI Aioga","description":"Everri ได้ตีพิมพ์บทความทบทวนประสบการณ์สําหรับ Fabre 5.1 ชื่อว่า Antropique Isso Bak (Argan) ไม่มีข้อความที่ถูกต้องในข้อความหลัก กรุณาอ้างอิงข้อความต้นฉบับสําหรับเนื้อหาการประเมินเฉ...","url":"https://www.aioga.com/th/news/cmtj29bdi03leroh99l1xccw0/","contentTranslated":true,"sourceHash":"44803b036fce9f88","translatedAt":"2026-09-01T19:43:01.898Z"},"pl":{"title":"Recenzja doświadczenia z Fabre May Day Experience: Kora Antropique Isso (Argen)","summary":"Everri opublikował przegląd doświadczeń dla Fabre 5.1 zatytułowany Antropique Isso Bak (Argan). W tekście głównym nie podano żadnego poprawnego tekstu; prosimy odwołać się do oryginalnego tekstu w celu uzyskania konkretnej treści oceny.","category":"行业动态","source":"Every：最新文章（网页）","aggregationSource":"Every：最新文章（网页）","pageTitle":"Recenzja doświadczenia z Fabre May Day Experience: Kora Antropique Isso (Argen) - Aioga Wiadomości AI","description":"Everri opublikował przegląd doświadczeń dla Fabre 5.1 zatytułowany Antropique Isso Bak (Argan). W tekście głównym nie podano żadnego poprawnego tekstu; prosimy odwołać się do orygi...","url":"https://www.aioga.com/pl/news/cmtj29bdi03leroh99l1xccw0/","contentTranslated":true,"sourceHash":"44803b036fce9f88","translatedAt":"2026-09-01T19:43:10.988Z"}},"evidenceTier":"verified-news","reviewStatus":"automated-ingest","indexable":true,"editorialCover":""}}