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

871–880 of 1001 posts

Re: Claude Opus 4.7

#871

Post by Gareth321 »

zarzavat wrote: post #336
lanyard-textile wrote: post #200

This comment thread is a good learner for founders; look at how much anguish can be put to bed with just a little honest communication. 1. Oops, we're oversubscribed. 2. Oops, adaptive reasoning landed poorly / we have to do it for capacity reasons. 3. Here's how subscriptions work. Am I really writing this bullet point? As someone with a production application pinned on Opus 4.5, it is extremely difficult to tell ap…

These threads are always full of superstitious nonsense. Had a bad week at the AIs? Someone at Anthropic must have nerfed the model! The roulette wheel isn't rigged, sometimes you're just unlucky. Try another spin, maybe you'll do better. Or just write your own code.

Opus 4.6 did actually get dumber. The Director of AI at AMD logged a pretty detailed issue with receipts: https://github.com/anthropics/claude-code/issues/42796

Re: Claude Opus 4.7

#872

Post by robertfall »

pkilgore wrote: post #688
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…

Seconded. After disabling adaptive thinking and using a default higher thinking, I finally got the quality I'm looking for out of Opus 4.6, and I'm pleased with what I see so far in Opus 4.7. Whatever their internal evals say about adaptive thinking, they're measuring the wrong thing.

As far as I understand Opus 4.7 disregards the disable adaptive thinking flag. So if you're seeing it perform well, perhaps their evals are inline?

Re: Claude Opus 4.7

#873

Post by EmanuelB »

weird-eye-issue wrote: post #842
elAhmo wrote: post #835

Earlier quoted context omitted.

Its funny to think that with a model release Anthropic can slide in some instructions ("be a bit more detailed" or something similar) that affect the token output by a few percent, 5-10%, which will not be noticeable by most users but over the course of the year would bring solid growth (once the VC craze is over, if ever) and increase income. "Regular companies" would love to have a growth like that without effectiv…

I like how some people are accusing them of reducing the overall token usage to screw over Claude Code users and then there are yet other people that are accusing them of deliberately increasing token usage to screw over API users (or maybe to get subscription users to upgrade, I'm not really sure)

I think this is the case. In the early GPT-4 days I tested the same model side by side across the subscription and API. The API always produced a longer better answer. To me it felt like the API model was working how it was supposed to work while the subscription model tried to reduce its token usage. From a business perspective that would make sense. I then switched to API only because I felt like it was worth the extra cost.

I did a similar test with sonnet about 6 months ago and noticed no difference, except that the subscription was way cheaper than API access. This is not the case anymore, at least not for me. The subscription these days only lasts for a few requests before it hits the usage limit and goes over to ”extra usage” billing. Last week I burned through my entire subscription budget and 80$ worth of extra usage in about 1h. That is not sustainable for me and the reason I started looking at alternatives.

From a business perspective it all makes sense. Anthropic recently gave away a ton of extra usage for free. Now people have balance on their accounts that Anthropic needs to pay for with compute, suddenly they release a model that seem to burn those tokens faster than ever. Last week I felt like the model did the opposite, it was stopping mid implementation and forgetting things after only 2 turns. Based on the responses I got it seemed like they were running out of compute, lobotomized their model and made it think less, give shorter answers etc. Probably they are also doing A/B testing on every change so my experience might be wildly different from someone else.

Re: Claude Opus 4.7

#874

Post by weitendorf »

paulluuk wrote: post #836
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…

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 that. Much better to use it as a kind of pre-processing/noise-reduction step that filters out junk context.

I would say that right now the benefits are largest for this kind of work with medium-sized multimodal models. For example I have hooks/automation that use https://github.com/accretional/chromerpc to automatically screenshot UIs and then feed it into qwen-family models. It's more that I don't want to pay Opus to look at them or remember/be instructed to do that unless it goes through QA first.

Re: Claude Opus 4.7

#875

Post by Gareth321 »

driverdan wrote: post #750
ACCount37 wrote: post #352

Earlier quoted context omitted.

This is the same paranoid, anxious behavior that ChatGPT has. One hell of a bad sign.

Models are not paranoid or anxious, they do not think or have feelings. I know you're probably using those words as a metaphor but we need to be careful about anthropomorphizing LLMs.

As an accelerationist and transhumanist, no way! These models passed the Turing test years ago. When a thing is indistinguishable from human, it is human. Our brains are, after all, just a collection of learned memetic weights. Just ask the determinists.

Re: Claude Opus 4.7

#876

Post by rkuska »

JamesSwift wrote: post #460
simonw wrote: post #203

I'm finding the "adaptive thinking" thing very confusing, especially having written code against the previous thinking budget / thinking effort / etc modes: https://platform.claude.com/docs/en/build-with-claude/adapti... Also notable: 4.7 now defaults to NOT including a human-readable reasoning token summary in the output, you have to add "display": "summarized" to get that: https://platform.claude.com/docs/en/build-…

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 400 error.

https://platform.claude.com/docs/en/build-with-claude/adapti...

For my claude code I went with following config:

* /effort xhigh (in the terminal cli) - To avoid lazying

* "env": {"CLAUDE_CODE_DISABLE_1M_CONTEXT": "1"} (settings.json) - It seems like opus is just worse with larger context

* "display": "summarized" (settings.json) - To bring back summaries.

* "showThinkingSummaries": true (settings.json) - Should show extended thinking summaries in interactive sessions

Freaking wizardry.

Re: Claude Opus 4.7

#877

Post by otabdeveloper4 »

paulluuk wrote: post #836
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…

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.

Fundamentally they're the same technology with the same exact algorithms under the hood; only the post-training alignment differs.

That is, the difference you see is either placebo effect or you being lucky and better aligning with model post-training bias.

Re: Claude Opus 4.7

#878

Post by cageface »

trueno wrote: post #455

noticing sharp uptick in "i switched to codex" replies lately. a "codex for everything" post flocking the front page on the day of the opus 4.7 release me and coworker just gave codex a 3 day pilot and it was not even close to the accuracy and ability to complete & problem solve through what we've been using claude for. are we being spammed? great. annoying. i clicked into this to read the differences and initial exp…

On at least high effort level I find GPT 5.4 easily beats Opus 4.6 in code generation and debugging issues.

Re: Claude Opus 4.7

#879

Post by 100ms »

trueno wrote: post #455

noticing sharp uptick in "i switched to codex" replies lately. a "codex for everything" post flocking the front page on the day of the opus 4.7 release me and coworker just gave codex a 3 day pilot and it was not even close to the accuracy and ability to complete & problem solve through what we've been using claude for. are we being spammed? great. annoying. i clicked into this to read the differences and initial exp…

I originally switched to Opus because it could reliably write Rust. As of 2 weeks ago, I'm using Codex because it writes way more compact and idiomatic Rust. Just another anecdote for the pile. I detest ChatGPT's persona, but Codex definitely feels better than Claude Code for anything I throw at it

Re: Claude Opus 4.7

#880

Post by hirako2000 »

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 ability to provide input.

I do not want an LLM to deep think, in most cases. Why not letting me disable deep thinking altogether. That's where engineers are likely heading: control.

Post reply on HN