Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Claude Fable 5.1 and Claude Mythos 5.1

anthropic.com

Post reply on HN
Print view View original

801–810 of 1001 posts

Re: Claude Fable 5.1 and Claude Mythos 5.1

#801

Post by gls2ro »

NL807 wrote: post #772
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…

Not sure if something like this is already on the table, but I would like to see Claude responses more in line with Simplified Technical English [1] by default. I find those writing styles a lot easier to read. This has been standardised as ASD-STE100 [2]. I've seen few people making SKILL.md files with that in mind, which works great, but having this by default without invoking the skill command would be better. 1.…

IMO that would be a mistake because Simplified Technical English cannot properly represent business domains specifically when talking about using specific concepts from those domains. It can explain those concepts but I think it will fail short or naming them.

So I think making that default as it is will create bugs. I ran an experiment here https://allaboutcoding.ghinda.com/explain-to-me-in-simple-te... (of course it is fit to my usage) see section "What about understanding and facts" and ASD-STE100 fails, in my experiment, to return facts as I have defined them in those cases compared with no instruction or just saying "use Simple Technical English".

Re: Claude Fable 5.1 and Claude Mythos 5.1

#802

Post by Bluestein »

anthonyrstevens wrote: post #645
Bluestein wrote: post #28

Unless these people start offering free, unlimited inference for a cautionary period so we can test the new model without an up-front (re-)investment, I am not touching this load-bearing pile of neuralese spew with a ten thousand token pole.-

Are you going to post the same comment on every AI article on HN? How is this useful to the discussion?

This, is the first time I have not only made this comment, but opined on this issue at all, actually.-

Re: Claude Fable 5.1 and Claude Mythos 5.1

#803

Post by bandrami »

mlaux wrote: post #46

Looks like all three breaking changes are patches for inadvertent chain of thought disclosure. Someone found out (don't have the tweet handy) that if you created a bogus "think_deeply" tool and then forced the model to use it, it would output what is believed to be its raw thinking there - I believe the first breaking change stops this. The second two are aimed at people getting Haiku to repeat thinking blocks from o…

Aren't the "thinking" chains always just reconstructed anyways? It would be like using a debugger that just looks at the source code rather than the actual binary.

Re: Claude Fable 5.1 and Claude Mythos 5.1

#804

Post by EagnaIonat »

exabrial wrote: post #419

Anyone ever seen the SouthPark episode making fun of Game of Thrones: A Song of Ass and Fire? Anthropic's announcements reminds me of "The Dragons Are Coming" running joke. What they have done: * Nerfed Fable, as many of noted it's useless * Leverage Mythos as a marketing strategy, claiming its too good to release * Removed thought traces, one of the only useful things to make sure your prompts are working correctly…

> Push a bunch of EU Overregulation onto the rest of the world with text watermarking,

That's not part of the EU regulations. You only need to say that it is created by AI, and then only under certain conditions.

Re: Claude Fable 5.1 and Claude Mythos 5.1

#805

Post by aennassiri »

anthonyrstevens wrote: post #628
aennassiri wrote: post #263

Earlier quoted context omitted.

We will have more bugs. Even the best models with the best software engineers will produce bugs. There are two reasons : first the pressure to produce more and second LLMs will always produce slop

>> LLMs will always produce slop Such a low-quality comment

What are your arguments then ? What are your thoughts ? I use fable everyday and it is always coming up with changes on thousands of files for simple things, overall the code does the job but there is always marginal slop or unnecessary code to be addressed.

Re: Claude Fable 5.1 and Claude Mythos 5.1

#806

Post by Razengan »

exabrial wrote: post #419

Anyone ever seen the SouthPark episode making fun of Game of Thrones: A Song of Ass and Fire? Anthropic's announcements reminds me of "The Dragons Are Coming" running joke. What they have done: * Nerfed Fable, as many of noted it's useless * Leverage Mythos as a marketing strategy, claiming its too good to release * Removed thought traces, one of the only useful things to make sure your prompts are working correctly…

Not to mention, the last time I tried them, and per the comments of other users:

* Letting you Sign-Up-with-Apple on iOS but not Sign-In-with-Apple on web, but supporting Sign-In-with-Google

* Not letting you remove your payment info

* Not letting you change your email

* Seemingly no way to get real support

Re: Claude Fable 5.1 and Claude Mythos 5.1

#807

Post by mirekrusin »

madrox wrote: post #405

I am finding that I am now less interested in better models than I am in token budgets. My issue with Anthropic models now is that I don't feel like I can rely on them as a daily driver because they'll dry up before my quota resets. I am becoming dependent on AI to make a living, and I need predictable spend on it. If I know I can't use a model regularly all month, my enthusiasm is limited. I urge Anthropic to get be…

Invest a bit of your time into optimising usage cost. Anthropic has first class docs, actually read it or ask llm to read them all for you and summarise most important points / ask to to reflect it on your .md files. Maybe silly thing like dropping your default thinking effort by one level or adding (sub)agent pinned to other model is all there it to completely fix it or maybe you have instructions that encourage big dumps in CLAUDE.md/AGENTS.md that needs splitting so progressive disclosure works correctly? Naively sending everything to the most expensive model on high thinking effort is anti pattern and will drain quota quickly.

My personal guess is that it's one of those. With effective context engineering it's hard to use all 20x quota, the limit becomes your own attention and time really.

You may argue that you're doing multiple, parallel extreme effort tasks – which may be true but then again, there will be results to actually look at sooner or later and that takes time.

Re: Claude Fable 5.1 and Claude Mythos 5.1

#808

Post by jamiek88 »

unsupp0rted wrote: post #688
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…

It's because GPT Sol is equally good and established a price ceiling

Sol is excellent. I’m amazed I can use it on my teeny $20 plan.

Re: Claude Fable 5.1 and Claude Mythos 5.1

#810

Post by lwansbrough »

alansaber wrote: post #809

The bar has dropped when the dialogue evolves to "output is less annoying" rather than some interesting new capability

On the contrary, I think the novelty of AI blowing our minds with each release has worn off a bit. These are some impressive improvements in science benchmarks. But we're sort of used to seeing impressive improvements now.

That doesn't make them less impressive, it just means people are shifting their focus more towards their own day to day experience with these things because we're relying on them so much now.

Like when the novelty of the automobile wore off, I'm sure people were starting to say "it's a bumpy ride though, isn't it?"

Post reply on HN