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

821–830 of 1001 posts

Re: Claude Opus 4.7

#821

Post by taffydavid »

malfist wrote: post #476
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 don't know, I think java is the best programming language. I use it for everything I do, no other programming language comes close. Python lost all my trust with how slow it's interpreter is, you can't use it for anything. ^^^^ Sarcastic response, but engineers have always loved their holy wars, LLM flavor is no different.

Java is great and all but if you don't use it with the right kind of keyboard you're wasting your time.

I use one of those very loud clacky ones with brightly colored keys and that makes me a better person

Re: Claude Opus 4.7

#822

Post by Scrounger »

parasti wrote: post #809
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…

Which open weights model?

> Which open weights model?

Yes, I'm also wondering!

Currently I'm testing out gemma4:26b and qwen3.6:35b-a3b-q4_K_M locally on my M2 Max Macbook Pro.

Not the fastest, but reasonable.

However, I am also interested in getting as close as possible in performance to Opus 4.6 while minimizing my costs.

Re: Claude Opus 4.7

#823

Post by hk__2 »

Scrounger wrote: post #822
parasti wrote: post #809

Earlier quoted context omitted.

Which open weights model?

> Which open weights model? Yes, I'm also wondering! Currently I'm testing out gemma4:26b and qwen3.6:35b-a3b-q4_K_M locally on my M2 Max Macbook Pro. Not the fastest, but reasonable. However, I am also interested in getting as close as possible in performance to Opus 4.6 while minimizing my costs.

> I am also interested in getting as close as possible in performance to Opus 4.6 while minimizing my costs.

Aren’t we all? ;)

Re: Claude Opus 4.7

#825

Post by taffydavid »

ed_mercer wrote: post #713
andai wrote: post #679

Earlier quoted context omitted.

Well, I can share my experience from a few days ago. Gave the same task (a major refactor) to both Claude and Codex. Codex finished in 5 minutes, Claude was still spinning after 20 minutes. Also it used up all my usage, about twice over (the 5-hour window rolled over in the middle of the task, so the usage for one task added up to 192%). Codex usage was 9%. So, 21x difference there, lol They're saying there's bugs la…

> Claude was still spinning after 20 minutes. I have been using Claude Code on a medium codebase (~2000 files, ~1M lines of code) for over a year and have never had to wait this long. Also I'm on the max plan and have not seen these limits at all.

Just yesterday it thought for 591 seconds for me, which is ten minutes. There have been times this week when it ran longer and I assumed it was just bust and stopped it

Re: Claude Opus 4.7

#826

Post by taffydavid »

Scrounger wrote: post #822
parasti wrote: post #809

Earlier quoted context omitted.

Which open weights model?

> Which open weights model? Yes, I'm also wondering! Currently I'm testing out gemma4:26b and qwen3.6:35b-a3b-q4_K_M locally on my M2 Max Macbook Pro. Not the fastest, but reasonable. However, I am also interested in getting as close as possible in performance to Opus 4.6 while minimizing my costs.

Gemma4 on an m2? That sounds promising. I have an m3 max, going to try that today

Re: Claude Opus 4.7

#827

Post by wsmhj »

Tried 4.7 on a few of my regular workloads. The quality ceiling is definitely higher than 4.6 when it actually engages — but that's the problem. "Adaptive thinking" seems to actively avoid thinking on tasks where I'd expect it to reason carefully, and I end up getting flat, fast answers where I wanted depth. Turning off adaptive thinking and bumping effort to high gets me closer to what I want, but at that point the token cost becomes hard to justify vs. just using a smaller model with explicit CoT. Feels like Anthropic is solving a cost optimization problem and calling it a feature.

Re: Claude Opus 4.7

#828

Post by smolder »

wsmhj wrote: post #827

Tried 4.7 on a few of my regular workloads. The quality ceiling is definitely higher than 4.6 when it actually engages — but that's the problem. "Adaptive thinking" seems to actively avoid thinking on tasks where I'd expect it to reason carefully, and I end up getting flat, fast answers where I wanted depth. Turning off adaptive thinking and bumping effort to high gets me closer to what I want, but at that point the…

Thank you for sharing.

Re: Claude Opus 4.7

#829

Post by misja111 »

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'm actually seeing a similar thing when comparing 4.6 and 4.5. It burns a lot more tokens, does show more how it is thinking along the way, but I don't see a strong difference in the end result. Occasionally 4.6 even seems to get stuck in its 'processing' phase, while 4.5 doesn't on the same task.
Post reply on HN