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

Claude Opus 4.7

anthropic.com

Post reply on HN
Print view View original

901–910 of 1001 posts

Re: Claude Opus 4.7

#901

Post by arcanemachiner »

rkuska wrote: post #876
JamesSwift wrote: post #460

Earlier quoted context omitted.

Its especially concerning / frustrating because boris’s reply to my bug report on opus being dumber was “we think adaptive thinking isnt working” and then thats the last I heard of it: https://news.ycombinator.com/item?id=47668520 Now disabling adaptive thinking plus increasing effort seem to be what has gotten me back to baseline performance but “our internal evals look good“ is not good enough right now for what ma…

For 4.7 it is no longer possible to disable adaptive thinking. Which is weird given the comment from Boris followed with silence (and closed github issue). So much for the transparency. > Claude Opus 4.7 (claude-opus-4-7), adaptive thinking is the only supported thinking mode. Thinking is off unless you explicitly set thinking: {type: "adaptive"} in your request; manual thinking: {type: "enabled"} is rejected with a…

It's early days for Opus 4.7, but I will say this: Today, I had a conversation go well into the 200K token range (I think I got up to 275K before ending the session), and the model seemed surprisingly capable, all things beings considered.

Particularly when compared to Opus 4.6, which seems to veer into the dumb zone heavily around the 200k mark.

It could have just been a one-off, but I was overall pleased with the result.

Re: Claude Opus 4.7

#904

Post by michaelscott »

mattmanser wrote: post #838
EmanuelB wrote: post #808

I can't notice any difference to 4.6 from 3 weeks ago, except that this model burns way more tokens, and produces much longer plans. To me it seem like this model is just the same as 4.6 but with a bigger token budget on all effort levels. I guess this is one way how Anthropic plans to make their business profitable. During the past weeks of lobotomized opus, I tried a few different open weight models side by side wi…

I just don't believe you. The vast gulf between open weights and frontier models that existed 6 months ago has suddenly disappeared? It's far more likely you're just bad at assessing model output.

Their problem space may be just fine with open weight models regardless, but yes the release of gemma 4, GLM 5.1 and qwen 3.5 (and now 3.6!) have all happened in the last 6 months

Re: Claude Opus 4.7

#905

Post by user34283 »

GaryBluto wrote: post #377
gpm wrote: post #354

Interestingly github-copilot is charging 2.5x as much for opus 4.7 prompts as they charged for opus 4.6 prompts (7.5x instead of 3x). And they're calling this "promotional pricing" which sounds a lot like they're planning to go even higher. Note they charge per-prompt and not per-token so this might in part be an expectation of more tokens per prompt. https://github.blog/changelog/2026-04-16-claude-opus-4-7-is-...

Not that anybody can actually use it though, as a large percentage of Copilot users are facing seemingly random multi-day rate limits. https://www.theregister.com/2026/04/15/github_copilot_rate_l...

I don’t know about rate limits, but I’ve been running into timeouts with Sonnet 4.6 after they don’t complete within 4-5 mins.

I have not encountered the same issues when using Claude Code.

Perhaps Copilot is on some sort of second rate priority.

Of course it’s the only thing available in our Enterprise, making us second class users.

Using the Copilot Business Plan we get the same rate limits as the student tier, making it infeasible to use Opus. Meanwhile management talks about their big plans for AI.

Re: Claude Opus 4.7

#907

Post by XCSme »

nisarg2 wrote: post #777
XCSme wrote: post #731

Earlier quoted context omitted.

The reasoning modes are really weird with 4.7 In my tests, asking for "none" reasoning resulted in higher costs than asking for "medium" reasoning... Also, "medium" reasoning only had 1/10 of the reasoning tokens 4.6 used to have.

Insane! Even Haiku doesn't make such mistakes.

I am not sure it's a mistake, this might be their new "adaptive reasoning" + hidden reasoning trace, so we can't verify.

Re: Claude Opus 4.7

#908

Post by concats »

hirako2000 wrote: post #880

I can understand the wishes to make LLMs even more self driven. After all that's the idea of a lose prompt. No matter how short, LLM figures out what most users are expecting. Thanks to RLHL it accomplishes wonders. My desire though is to be able to steer the model exactly where I want. Assuming token cost isn't an issue, it doesn't remove the need for costly review. I would rather think first and polish up my abilit…

The recently viral 'grill-me' skill is great for exactly this.

It's just a super simple skill that, when invoked, makes the model spend considerable time asking design and architecture questions and fleshing out any plan with you. A planning session without it might be Claude asking you 2 questions, and with it 22.

Re: Claude Opus 4.7

#909

Post by embedding-shape »

weitendorf wrote: post #874
paulluuk wrote: post #836

Earlier quoted context omitted.

If open weight models are sufficient for your engineering problems, then you should absolutely use them. But I haven't seen a single open weight model that can get even close to the complexity in my projects. They sometimes work for small toy examples or leetcode puzzles, but not very any real project. Really curious what models you've found that could replace current state of the art.

I find the most value to be in eval loops and multi-agent setups where a specialized or cheap model gets tasks that take load off the smarter model. Most of the value in agentic development IMO is in the feedback loop/ability for the model itself to intelligently pull in context, but if you want to push a lot of context or have steps that are more proscribed, it's kind of a waste of money to have the big model do tha…

> I find the most value to be in eval loops and multi-agent setups where a specialized or cheap model gets tasks that take load off the smarter model.

Yes, in theory, this should hold up, at least according to evaluations.

According to real, practical use though, none of the open weight models are generally strong enough to handle coding and programming in a professional environment though, unless you have tightly controlled scope and specialized models for those scopes, which generally I don't think you have, but maybe it's just me jumping around a lot.

Even with feedback loops, harnesses and what not, even the strongest local models I can run with 96GB of VRAM don't seem to come close to what OpenAI offered in the last year or so. I'm sure it'll be ready at one point, but today it isn't.

With that said, if you know specific models you think work well as a general and local programming models, please share which ones, happy to be shown wrong. Latest I've tried was Qwen3.6-35B-A3B which gets a bit further but still instruction following is a far cry from what OpenAI et al offered for years.

Re: Claude Opus 4.7

#910

Post by thaanpaa »

beaker52 wrote: post #893
JamesSwift wrote: post #460

Earlier quoted context omitted.

Its especially concerning / frustrating because boris’s reply to my bug report on opus being dumber was “we think adaptive thinking isnt working” and then thats the last I heard of it: https://news.ycombinator.com/item?id=47668520 Now disabling adaptive thinking plus increasing effort seem to be what has gotten me back to baseline performance but “our internal evals look good“ is not good enough right now for what ma…

It doesn’t really come as a surprise to me that these companies are struggling to reliably fix issues with software which relies on a central component which is nondeterministic. But they made their own bed with that one.

Well, the fun part is that the algorithms themselves are deterministic. They are just so afraid of model distillation that they force some randomness on top (and now hide thinking). Arguably for coding, you'd probably want temperature=0, and any variation would be dependent on token input alone.
Post reply on HN