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

771–780 of 1001 posts

Re: Claude Opus 4.7

#771

Post by solenoid0937 »

raylad wrote: post #751

I am using 4.7 with the default extra high thinking, and it is clearly very stupid. It's worse than old Sonnet 4.5. I had it suggest some parameters for BCFtools and it suggested parameters that would do the opposite of what I wanted to do. I pointed out the error and it apologized. It also is not taking any initiative to check things, but wants me to check them (ie: file contents, etc.). And it is claiming that thin…

It's been dramatically better than any model I have ever used before on my tasks.

Re: Claude Opus 4.7

#772

Post by oezi »

I think I would love to test it, but on the Pro plan I just did two small sessions with 4.6 Sonnet and it consumed my 5h quota within one hour.

Re: Claude Opus 4.7

#773

Post by zhonghuajin »

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-…

[flagged]

Re: Claude Opus 4.7

#774

Post by sheeshkebab »

So they nixed the fun part of working with the bot - reading its thinking output. Now this thing just plain unfun and often stupid.

So, yeah, good job anthropic. Big fuck you to you too.

Re: Claude Opus 4.7

#775

Post by djmips »

simonw wrote: post #485
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-…

... here's the pelican, I think Qwen3.6-35B-A3B running locally did a better job! https://simonwillison.net/2026/Apr/16/qwen-beats-opus/

Opus did get the feet on pedals better.

Re: Claude Opus 4.7

#776

Post by shepherdjerred »

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’m slowly switching to codex simply because Claude code is closed source and I want to hack on my harness.

Re: Claude Opus 4.7

#777

Post by nisarg2 »

XCSme wrote: post #731
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-…

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.

Re: Claude Opus 4.7

#780

Post by 4b11b4 »

cupofjoakim wrote: post #20

> Opus 4.7 uses an updated tokenizer that improves how the model processes text. The tradeoff is that the same input can map to more tokens—roughly 1.0–1.35× depending on the content type. caveman[0] is becoming more relevant by the day. I already enjoy reading its output more than vanilla so suits me well. [0] https://github.com/JuliusBrussee/caveman/tree/main

but what about DDD
Post reply on HN