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

611–620 of 1001 posts

Re: Claude Opus 4.7

#611

Post by Computer0 »

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 but I find even the way the model writes in codex to be harder to read. The usage limits in Codex were very generous the past year until this week.

Re: Claude Opus 4.7

#613

Post by mnicky »

HarHarVeryFunny wrote: post #266
u_sama wrote: post #5

Excited to use 1 prompt and have my whole 5-hour window at 100%. They can keep releasing new ones but if they don't solve their whole token shrinkage and gaslighting it is not gonna be interesting to se.

It seems a lot of the problem isn't "token shrinkage" (reducing plan limits), but rather changes they made to prompt caching - things that used to be cached for 1 hour now only being cached for 5 min. Coding agents rely on prompt caching to avoid burning through tokens - they go to lengths to try to keep context/prompt prefixes constant (arranging non-changing stuff like tool definitions and file content first, varia…

> things that used to be cached for 1 hour now only being cached for 5 min.

Doesn't this only apply to subagents, which don't have much long-time context anyway?

Re: Claude Opus 4.7

#615

Post by SEJeff »

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.

I believe tools like graphify cut down the tokens in thinking dramatically. It makes a knowledge graph and dumps it into markdown that is honestly awesome. Then it has stubs that pretend to be some tools like grep that read from the knowledge graph first so it does less work. Easy to setup and use too. I like it.

https://graphify.net/

Re: Claude Opus 4.7

#616

Post by solenoid0937 »

frankdenbow wrote: post #523
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…

we arent bots because we disagree with you. I switch between codex and opus, they have their differing strengths. As many people have mentioned, opus in the past few weeks has had less than stellar results. Generally I find opus would rather stub something and do it the faster way than to do a more complete job, although its much better at front end. I've had times where I've thrown the same problem at opus 4/5 times…

[flagged]

Re: Claude Opus 4.7

#617

Post by brunooliv »

I’ve been using Opus 4.6 extensively inside Claude Code via AWS Bedrock with max effort for a few months now (since release). I’ve found a good “personal harness” and way of working with it in such a way that I can easily complete self contained tasks in my Java codebase with ease.

Now idk if it’s just me or anything else changed, but, in the last 4/5 days, the quality of the output of Opus 4.6 with max effort has been ON ANOTHER LEVEL. ABSOLUTELY AMAZING! It seems to reason deeper, verifies the work with tests more often, and I even think that it compacted the conversations more effectively and often. Somehow even the quality of the English “text” in the output felt definitely superior. More crisp, using diagrams and analogies to explain things in a way that it completely blew me away. I can’t explain it but this was absolutely real for me.

I’d say that I can measure it quite accurately because I’ve kept my harness and scope of tasks and way of prompting exactly the same, so something TRULY shifted.

I wish I could get some empirical evidence of this from others or a confirmation from Boris…. But ISTG these last few days felt absolutely incredible.

Re: Claude Opus 4.7

#618

Post by solenoid0937 »

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…

OAI marketing/PR in overdrive:

1. Subsidize compute unsustainably

2. Trick a bunch of people into thinking you're more pro-developer than the other guy [we are here]

3. Rug pull when you have enough market share.

Re: Claude Opus 4.7

#619

Post by frankdenbow »

solenoid0937 wrote: post #616
frankdenbow wrote: post #523

Earlier quoted context omitted.

we arent bots because we disagree with you. I switch between codex and opus, they have their differing strengths. As many people have mentioned, opus in the past few weeks has had less than stellar results. Generally I find opus would rather stub something and do it the faster way than to do a more complete job, although its much better at front end. I've had times where I've thrown the same problem at opus 4/5 times…

[flagged]

So what am i then? i only replied to someone claiming people are bots for having an opinion. I use opus regularly and its great.

Re: Claude Opus 4.7

#620

Post by JohnMakin »

drewnick wrote: post #233
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…

Hasn't Opus 4.5 been famously consistent while 4.6 was floating all over the place?

I'm still on 4.5. My coworkers are describing a lot of problems I just don't have. I suspect it was some combination of the larger context window, the model itself, and various bugs like the cache miss thing reported a little while ago.
Post reply on HN