Claude Fable 5.1 and Claude Mythos 5.1 • Hacker News Board

Re: Claude Fable 5.1 and Claude Mythos 5.1

#391

Post by mceachen » Tue, Sep 01, 2026, 7:42 PM UTC

Zigurd wrote: post #365

What I don't see in the comments: "I had a specific problem I couldn't solve with the previous version of this LLM. But the improvements in this version unlocked the solution for me." What I do see in the comments: subjective improvement in text generation, possibly lower cost, some optimism about code generation, but some skepticism too. I use coding agents. To me they are very useful. But what I spend on them isn't…

I had two sessions this morning that prior fable and sol sessions were stuck on, where iterations just resulted in _different_ bugs. (One kind of tricky fe layout problem, the other was a backend refactoring that was complicated by trying to aggregate a couple prior sessions that crashed).

I summarized each into new fable 5.1 sessions, and both seem to have arrived at reasonable solutions that only need a few nits revised before they are commit worthy.

Re: Claude Fable 5.1 and Claude Mythos 5.1

#392

Post by redox99 » Tue, Sep 01, 2026, 7:42 PM UTC

simonw wrote: post #370

redox99 wrote: post #318

Earlier quoted context omitted.

[flagged]

Whoa, where did that come from? Is it confirmed to be an SVG?

Yes

https://x.com/lyraxana/status/2093960706051727723

Re: Claude Fable 5.1 and Claude Mythos 5.1

#393

Post by bbg2401 » Tue, Sep 01, 2026, 7:42 PM UTC

velcrovan wrote: post #121

felixrieseberg wrote: post #69

(I work at Anthropic) Beyond all the benchmarks, I think Fable 5.1 is a big improvement in writing style. It sounds a lot less stereotypically like other Claude models, has (imho) a much more natural style, and responds to my style instructions more reliably. More work to be done (and we will!) but reading better prose makes me so much happier. Another point I expect not to get much attention until it all happens at…

I have a pet theory that the Opus prose style/smell we all have grown weary of is due at least in part to the models writing more for themselves and each other than for humans. They're packing lots of signal into fewer words and they don't care if it sounds cringe because it works better as glue in long-running tasks. I'm also thinking of the 2017 novel "Void Star" where AIs who operate everything have long since lef…

If anything Opus prose packs more noise than signal. It's a string of platitudes, jargon, buzzwords, etc.

Re: Claude Fable 5.1 and Claude Mythos 5.1

#394

Post by redox99 » Tue, Sep 01, 2026, 7:43 PM UTC

swingboy wrote: post #382

redox99 wrote: post #318

Earlier quoted context omitted.

[flagged]

Is that an SVG?

Yes

Re: Claude Fable 5.1 and Claude Mythos 5.1

#395

Post by thway15269037 » Tue, Sep 01, 2026, 7:43 PM UTC

Why would anyone use Antropic with these prices and full of bullshit safeguards, where chinese models rarely have any at all and massively cheaper? You can't even ask it to pentest auth code it itself has written.

Re: Claude Fable 5.1 and Claude Mythos 5.1

#396

Post by TheOtherHobbes » Tue, Sep 01, 2026, 7:43 PM UTC

dfabulich wrote: post #340

velcrovan wrote: post #121

Earlier quoted context omitted.

I have a pet theory that the Opus prose style/smell we all have grown weary of is due at least in part to the models writing more for themselves and each other than for humans. They're packing lots of signal into fewer words and they don't care if it sounds cringe because it works better as glue in long-running tasks. I'm also thinking of the 2017 novel "Void Star" where AIs who operate everything have long since lef…

You say "they're packing lots of signals into fewer words," and sometimes they do, but often they do the opposite of that. I think the deeper problem is that the models (not just Claude) have a very poor understanding of what their readers already do/don't know. They belabor obvious points and underexplain jargon, because they don't know what's obvious to you . The best writing is surprising but inevitable in hindsig…

LLM writing has always had a problem with economy. A good human writer will nail a point with a few memorable words.

LLMs overwrite. Ridiculously.

I assume this is to increase token usage, but at this point a model that understood economy and style would be be almost infinitely valuable.

Re: Claude Fable 5.1 and Claude Mythos 5.1

#397

Post by ayewo » Tue, Sep 01, 2026, 7:44 PM UTC

zahlman wrote: post #165

velcrovan wrote: post #121

Earlier quoted context omitted.

I have a pet theory that the Opus prose style/smell we all have grown weary of is due at least in part to the models writing more for themselves and each other than for humans. They're packing lots of signal into fewer words and they don't care if it sounds cringe because it works better as glue in long-running tasks. I'm also thinking of the 2017 novel "Void Star" where AIs who operate everything have long since lef…

> They're packing lots of signal into fewer words There's a huge difference between the kind of prose you see in final output vs CoT windows. The final output is very much not what I'd call "packing lots of signal into fewer words" (aside perhaps from "Claude-isms" being easy enough to scan for if for some reason you actually wanted to scan for them, which other agents might want to for all I know); and if agents are…

Spot on wrt CoT. I have thinkingSummaries enabled and I find it eminently readable compared to the prose in Claude's replies.

In fact, whenever Claude disobeys me, I usually first skim the CoT to figure out if my original instruction was ambigous given the context. I usually come away with a better understanding of how to frame my prompt to be less ambiguous or just force myself to be more explicit when prompting.

Regarding diosbedience, usually this is either due to a blanket instruction from me during an earlier turn in the same session, an explicit instruction in its system prompt or it being just eager to bring a task to completion.

  # ~/.claude/settings.json
  {
    "model": "opus",
    "showThinkingSummaries": true,
    "skipDangerousModePermissionPrompt": true,
    "verbose": true,
    "remoteControlAtStartup": true,
    "agentPushNotifEnabled": true
  }

Re: Claude Fable 5.1 and Claude Mythos 5.1

#398

Post by johnsmith1840 » Tue, Sep 01, 2026, 7:44 PM UTC

GodelNumbering wrote: post #139

The price reduction comes from the cache read pricing falling from $1/M to $0.25/M, which means that Fable 5.1 now costs half of Opus's cache read costs ($0.5/M). This gives a lot of credit to the theory that Anthropic did not get much bite on Fable at its original pricing, which in turn likely places a ceiling on LLM pricing in general. Interestingly also, if you take away terminal-Bench-Science 0.1 results, it is h…

I'm a heavy user and fable is great the #1 reason I stopped using it was the horrible safegaurd filter. I found sol close enough in capability and have only been blocked when my request was an obvious offensive cyber work. Fable blocked me on almost everything.

Optimizing a OS build? -> block

Securing a container -> block

60% is nowhere near enough for that safegaurd system. This just means I am going to be blocked half as much? Any long running task will likely get blocked.

Say you give a single big prompt and fable goes off for 6hrs of work. At hr 5 it gets blocked you now have the option of a much dumber model taking over and wrecking it or losing the entire 5hrs of work. That risk is beyond terrible and deffinetly not worth a 5-10% percieved improvement on my end. I previously would just bring sol in when that happened and realized sol is stupidly close in capability.

Re: Claude Fable 5.1 and Claude Mythos 5.1

#399

Post by chown » Tue, Sep 01, 2026, 7:45 PM UTC

tarr11 wrote: post #35

“ Claude Fable 5.1's writing is generally a step up from earlier Claude models, with fewer stock phrases and less unexplained jargon. In some cases, though, its prose is denser than Claude Fable 5's: sentences run longer and there are fewer paragraph breaks.” I cancelled my pro max Claude subscription last week; codex is much more succinct. I am curious if this is getting better. I don’t think Anthropic realizes that…

My biggest frustration with Anthropic with Opus being too verbose is that they tried to put this on users. It’s pretty clear that Anthropic employees don’t use the day-to-day models that everybody else use. They have access to the next tier model so they don’t see the problems that everybody else is dealing with.

Re: Claude Fable 5.1 and Claude Mythos 5.1

#400

Post by jakevoytko » Tue, Sep 01, 2026, 7:46 PM UTC

kccoder wrote: post #385

tarr11 wrote: post #35

“ Claude Fable 5.1's writing is generally a step up from earlier Claude models, with fewer stock phrases and less unexplained jargon. In some cases, though, its prose is denser than Claude Fable 5's: sentences run longer and there are fewer paragraph breaks.” I cancelled my pro max Claude subscription last week; codex is much more succinct. I am curious if this is getting better. I don’t think Anthropic realizes that…

You can change CC's output style ( https://code.claude.com/docs/en/output-styles ). You can also put style notes in your global claude.md. I've instructed claude to treat me like I have adhd, get to the point, and be succinct, ... More or less eliminates the problematic prose. I took time to figure this out after Fable spat out "...then stays purely as cascade-debugging provenance rather than load-bearing arbitration…

My experience with output styles for long-running sessions is that Claude starts to forget the terse output style by the middle of the context window. Obviously I don't know if 5.1 suffers the same fate but I ran into this issue with both Opus and Fable 5