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

731–740 of 1001 posts

Re: Claude Opus 4.7

#731

Post by XCSme »

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.

Re: Claude Opus 4.7

#732

Post by XCSme »

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.

Oh, and also, the "none" and "medium" variants performed the same (??)

Re: Claude Opus 4.7

#733

Post by xnx »

Tiberium wrote: post #36
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

I hope people realize that tools like caveman are mostly joke/prank projects - almost the entirety of the context spent is in file reads (for input) and reasoning (in output), you will barely save even 1% with such a tool, and might actually confuse the model more or have it reason for more tokens because it'll have to formulate its respone in the way that satisfies the requirements.

There's a tremendous amount of superstition around LLMs. Remember when "prompt engineering" "best practices" were to say you were offering a tip or some other nonsense?

Re: Claude Opus 4.7

#734

Post by AussieWog93 »

dbbk wrote: post #22
rvz wrote: post #13

Introducing a new upgraded slot machine named "Claude Opus" in the Anthropic casino. You are in for a treat this time: It is the same price as the last one [0] (if you are using the API.) But it is slightly less capable than the other slot machine named 'Mythos' the one which everyone wants to play around with. [1] [0] https://claude.com/pricing#api [1] https://www.anthropic.com/news/claude-opus-4-7

If you're building a standard app Opus is already good enough to build anything you want. I don't even know what you'd really need Mythos for.

Opus sometimes makes poor long term decisions and really struggles with even mid size (~10k lines) existing codebases.

Re: Claude Opus 4.7

#736

Post by dwood_dev »

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 use both. I avoided codex in late 2025 because it was slow as molasses. I tried it again in February and it was on par with Opus speed.

I like codex(gpt-5.4 high) more for its ability to nitpick my PRs and find bugs. I like opus 4.6 much better for anything dealing with visuals, but I feel its rule adherence is inferior and it is not nearly as thorough on code reviews.

I like working and building better with claude, I like fixing bugs better with codex. Also, claude is much better and faster evolving with skills, plugins, new features I find useful, etc. Codex is always a month behind or more.

I did both for a month at higher tiers, $200 Claude Max and $200 ChatGPT Pro. I was always having to conserve my usage with claude, with codex I could just let it run wild with no cares. In the end, I downgraded claude to the $20 plan and use it on occasion, and I have kept the $200 codex sub.

I also have Claude at work, so I'll know pretty soon if I want to swap subs again, but for now, I'm sticking with codex at home.

Re: Claude Opus 4.7

#737

Post by XCSme »

I was initially excited by 4.7, as it does a lot better in my tests, but their reasoning/pricing is really weird and unpredictable.

Apart from that, in real-life usage, gpt-5.3-codex is ~10x cheaper in my case, simply because of the cached input discount (otherwise it would still be around 3-4x cheaper anyway).

Re: Claude Opus 4.7

#738

Post by willsmith72 »

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

That's such a poor way to communicate a number. I take it they mean an increase of up to 35%?
Post reply on HN