Couldn't even tell the difference between brokerage and prime brokerage until I corrected it - yikes, I found that pretty annoying. I needed to correct him on something so basic and context-less.
Claude Opus 4.7
951–960 of 1001 posts
Re: Claude Opus 4.7
#952Too late, personally after how bad 4.6 was the past week I was pushed to codex, which seems to mostly work at the same level from day to day. Just last night I was trying to get 4.6 to lookup how to do some simple tensor parallel work, and the agent used 0 web fetches and just hallucinated 17K very wrong tokens. Then the main agent decided to pretend to implement tp, and just copied the entire model to each node...
I've been using it with `/effort max` all the time, and it's been working better than ever. I think here's part of the problem, it's hard to measure this, and you also don't know in which AB test cohorts you may currently be and how they are affecting results.
unless you always have run it on effort max, and see that it degraded.
Re: Claude Opus 4.7
#953Apparently they were A/B testing Opus 4.7 two weeks before officially released. Some requests were route to 4.7 occasionally when specifying Opus 4.6 for some accounts. https://matrix.dev/blog-2026-04-16.html
Very interesting, I wonder if this is some of the issues people were seeing
Re: Claude Opus 4.7
#954noticing 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 switched to Codex. What I noticed is that while Claude was a more elegant coder and more accurate in how it went about coding, Codex is more intelligent... hard to describe it. If I could have a subscription to both, I'd use Opus to plan and code, and then check the work and fix issues with Codex.
Re: Claude Opus 4.7
#955> "We are releasing Opus 4.7 with safeguards that automatically detect and block requests that indicate prohibited or high-risk cybersecurity uses. " This decision is potentially fatal. You need symmetric capability to research and prevent attacks in the first place. The opposite approach is 'merely' fraught. They're in a bit of a bind here.
OpenAI had been very strict about blocking reverse engineering/Ghidra/IDA_Pro-MCP tasks. I even got a warning email. I was having much more success convincing Claude Code for those tasks without warnings. Seems like they've tightened things up.
Re: Claude Opus 4.7
#956They've increased their cybersecurity usage filters to the point that Opus 4.7 refuses to work on any valid work, even after web fetching the program guidelines itself and acknowledging "This is authorized research under the [Redacted] Bounty program, so the findings here are defensive research outputs, not malware. I'll analyze and draft, not weaponize anything beyond what's needed to prove the bug to [Redacted]. I…
Came here to post this. 4.7 is absolutely useless for binary/firmware analysis on our own freakin products.
Anthropic needs to get their ish together I've got real work to do.
Re: Claude Opus 4.7
#957noticing 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 tried it again in February and it was on par with Opus speed.
I'm not finding that, like not even close. I'm using it mostly to write specs and docs and having Claude and Gippity check each other's work and fix things. It's looking into other previously written MD docs, and checking against 3-4 multi-thousand file Ruby codebase(s).
5.4 takes about 50% longer, almost without fail. I'm using 'medium' effort on both.
Re: Claude Opus 4.7
#958A gated, premium-tier product differentiation strategy only works when you sell the differentiated product. They went to market with 4.7 nerfed at security work and aren’t letting even large, vetted corporations pay more for the Mythos model… sentiment is quite negative where I work right now. There’s a real possibility that open source will give them a hair cut in the interim. And if the SWEs start modifying their CLI flows to avoid lock in to `claude`, it’s probable that the hair just never grows back. Losing strategy.
Re: Claude Opus 4.7
#959Claude Opus 4.7, on the web at least, really likes the word epistemics.
Re: Claude Opus 4.7
#960Earlier quoted context omitted.
Its especially concerning / frustrating because boris’s reply to my bug report on opus being dumber was “we think adaptive thinking isnt working” and then thats the last I heard of it: https://news.ycombinator.com/item?id=47668520 Now disabling adaptive thinking plus increasing effort seem to be what has gotten me back to baseline performance but “our internal evals look good“ is not good enough right now for what ma…
For 4.7 it is no longer possible to disable adaptive thinking. Which is weird given the comment from Boris followed with silence (and closed github issue). So much for the transparency. > Claude Opus 4.7 (claude-opus-4-7), adaptive thinking is the only supported thinking mode. Thinking is off unless you explicitly set thinking: {type: "adaptive"} in your request; manual thinking: {type: "enabled"} is rejected with a…
Your display and thinking summery settings aren’t working for me (v2.1.112 on macOS). Any advice?