Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Anonymous request-token comparisons from Opus 4.6 and Opus 4.7

tokens.billchambers.me

Post reply on HN
Print view View original

121–130 of 620 posts

Re: Anonymous request-token comparisons from Opus 4.6 and Opus 4.7

#121

Post by tiffanyh »

sync wrote: post #81
tiffanyh wrote: post #52

I was using Opus 4.7 just yesterday to help implement best practices on a single page website. After just ~4 prompts I blew past my daily limit. Another ~7 more prompts & I blew past my weekly limit. The entire HTMl/CSS/JS was less than 300 lines of code. I was shocked how fast it exhausted my usage limits.

Which plan are you on? I could see that happening with Pro (which I think defaults to Sonnet?), would be surprised with Max…

Pro. It even gave me $20 free credits, and exhausted free credits nearly instantly.

Re: Anonymous request-token comparisons from Opus 4.6 and Opus 4.7

#122

Post by post-it »

ahartmetz wrote: post #54
dakiol wrote: post #46

We dropped Claude. It's pretty clear this is a race to the bottom, and we don't want a hard dependency on another multi-billion dollar company just to write software We'll be keeping an eye on open models (of which we already make good use of). I think that's the way forward. Actually it would be great if everybody would put more focus on open models, perhaps we can come up with something like the "linux/postgres/git…

>we don't want a hard dependency on another multi-billion dollar company just to write software One of two main reasons why I'm wary of LLMs. The other is fear of skill atrophy. These two problems compound. Skill atrophy is less bad if the replacement for the previous skill does not depend on a potentially less-than-friendly party.

I was worried about skill atrophy. I recently started a new job, and from day 1 I've been using Claude. 90+% of the code I've written has been with Claude. One of the earlier tickets I was given was to update the documentation for one of our pipelines. I used Claude entirely, starting with having it generate a very long and thorough document, then opening up new contexts and getting it to fact check until it stopped finding issues, and then having it cut out anything that was granular/one query away. And then I read what it had produced.

It was an experiment to see if I could enter a mature codebase I had zero knowledge of, look at it entirely through an AI, and come to understand it.

And it worked! Even though I've only worked on the codebase through Claude, whenever I pick up a ticket nowadays I know what file I'll be editing and how it relates to the rest of the code. If anything, I have a significantly better understanding of the codebase than I would without AI at this point in my onboarding.

Re: Anonymous request-token comparisons from Opus 4.6 and Opus 4.7

#123

Post by ori_b »

tossandthrow wrote: post #105
ori_b wrote: post #92

Earlier quoted context omitted.

Yes, you certainly can argue that, but you'd be wrong. The primary selling point of LLMs is that they solve the problem of needing skill to get things done.

That is not the entire selling point - so you are very wrong. You very much decide how you employ LLMs. Nobody are keeping a gun to your head to use them. In a certain way. Sonif you use them in a way that increase you inherent risk, then you are incredibly wrong.

I suggest you read the sales pitches that these products have been making. Again, when I say that this is the selling point, I mean it: This is why management is buying them.

Re: Anonymous request-token comparisons from Opus 4.6 and Opus 4.7

#124

Post by maleldil »

templar_snow wrote: post #67
bakugo wrote: post #34

Earlier quoted context omitted.

How do you justify the API and web UI versions of 4.7 refusing to solve NYT Connections puzzles due to "safety"? https://x.com/LechMazur/status/2044945702682309086

To be fair, reading the New York Times is a safety risk for any intelligent life form these days. But still.

You don't need to subscribe to the NYT to play the games. There's a separate subscription.

Re: Anonymous request-token comparisons from Opus 4.6 and Opus 4.7

#125

Post by bobjordan »

I've spent the past 4+ months building an internal multi-agent orchestrator for coding teams. Agents communicate through a coordination protocol we built, and all inter-agent messages plus runtime metrics are logged to a database.

Our default topology is a two-agent pair: one implementer and one reviewer. In practice, that usually means Opus writing code and Codex reviewing it.

I just finished a 10-hour run with 5 of these teams in parallel, plus a Codex run manager. Total swarm: 5 Opus 4.7 agents and 6 Codex/GPT-5.4 agents.

Opus was launched with:

`export CLAUDE_AUTOCOMPACT_PCT_OVERRIDE=35 claude --dangerously-skip-permissions --model 'claude-opus-4-7[1M]' --effort high --thinking-display summarized`

Codex was launched with:

`codex --dangerously-bypass-approvals-and-sandbox --profile gpt-5-4-high`

What surprised me was usage: after 10 hours, both my Claude Code account and my Codex account had consumed 28% of their weekly capacity from that single run.

I expected Claude Code usage to be much higher. Instead, on these settings and for this workload, both platforms burned the same share of weekly budget.

So from this datapoint alone, I do not see an obvious usage-efficiency advantage in switching from Opus 4.7 to Codex/GPT-5.4.

Re: Anonymous request-token comparisons from Opus 4.6 and Opus 4.7

#126

Post by boxingdog »

ahartmetz wrote: post #54
dakiol wrote: post #46

We dropped Claude. It's pretty clear this is a race to the bottom, and we don't want a hard dependency on another multi-billion dollar company just to write software We'll be keeping an eye on open models (of which we already make good use of). I think that's the way forward. Actually it would be great if everybody would put more focus on open models, perhaps we can come up with something like the "linux/postgres/git…

>we don't want a hard dependency on another multi-billion dollar company just to write software One of two main reasons why I'm wary of LLMs. The other is fear of skill atrophy. These two problems compound. Skill atrophy is less bad if the replacement for the previous skill does not depend on a potentially less-than-friendly party.

[dead]

Re: Anonymous request-token comparisons from Opus 4.6 and Opus 4.7

#127

Post by pitched »

zozbot234 wrote: post #73
blahblaher wrote: post #56

Earlier quoted context omitted.

qwen3.5/3.6 (30B) works well,locally, with opencode

Mind you, a 30B model (3B active) is not going to be comparable to Opus. There are open models that are near-SOTA but they are ~750B-1T total params. That's going to require substantial infrastructure if you want to use them agentically, scaled up even further if you expect quick real-time response for at least some fraction of that work. (Your only hope of getting reasonable utilization out of local hardware in sing…

For a business with ten or more engineers/people-using-ai, it might still make sense to set this up. For an individual though, I can’t imagine you’d make it through to positive ROI before the hardware ages out.

Re: Anonymous request-token comparisons from Opus 4.6 and Opus 4.7

#129

Post by zozbot234 »

pitched wrote: post #117
jherdman wrote: post #102

Earlier quoted context omitted.

Is this sort of setup tenable on a consumer MBP or similar?

For a 30B model, you want at least 20GB of VRAM and a 24GB MBP can’t quite allocate that much of it to VRAM. So you’d want at least a 32GB MBP.

It's a MoE model so I'd assume a cheaper MBP would simply result in some experts staying on CPU? And those would still have a sizeable fraction of the unified memory bandwidth available.

Re: Anonymous request-token comparisons from Opus 4.6 and Opus 4.7

#130

Post by boxingdog »

dakiol wrote: post #46

We dropped Claude. It's pretty clear this is a race to the bottom, and we don't want a hard dependency on another multi-billion dollar company just to write software We'll be keeping an eye on open models (of which we already make good use of). I think that's the way forward. Actually it would be great if everybody would put more focus on open models, perhaps we can come up with something like the "linux/postgres/git…

[dead]
Post reply on HN