141–150 of 829 posts
That analysis is pretty brutal. It's very disconcerting that they can sell access to a high quality model then just stealthily degrade it over time, effectively pulling the rug from under their customers.
First time interacting with a corporation in America?
Earlier quoted context omitted.
What I've noticed is that whenever Claude says something like "the simplest fix is..." it's usually suggesting some horrible hack. And whenever I see that I go straight to the code it wants to write and challenge it.
That is the kind of thing that I've been fighting by being super explicit in CLAUDE.md. For whatever reason, instead of being much more thorough and making sure that files are being changed only after fully understanding the scope of the change (behaviour prior to Feb/Mar), Claude would just jump to the easiest fix now, with no backwards compatibility thinking and to hell with all existing tests. What is even worse i…
Earlier quoted context omitted.
There is a huge difference between greenfield development and working with an existing codebase. I'm not trying to discredit your experience and maybe it really is something wrong with the model. But in my experience those first few prompts / features always feel insanely magical, like you're working with a 10x genius engineer. Then you start trying to build on the project, refactor things, deploy, productize, etc. a…
This has been my (admittedly limited) experience as well. LLMs are great at initial bring-up, good at finding bugs, bad at adding features. But I'm optimistic that this will gradually improve in time.
The codebase itself is architected and documented to be LLM friendly and claude.md gives very strong harnesses how to do things.
As architect Claude is abysmal, but when you give it an existing software pattern it merely needs to extend, it’s so good it still gives me probably something like 5x feature velocity boost.
Plus when doing large refactorings, it forgets much fever things than me.
Inventing new architecture is as hard as ever and it’s not great help there - unless you can point it to some well documented pattern and tell it ”do it like that please”.
Earlier quoted context omitted.
What I've noticed is that whenever Claude says something like "the simplest fix is..." it's usually suggesting some horrible hack. And whenever I see that I go straight to the code it wants to write and challenge it.
lol this one time Claude showed me two options for an implementation of a new feature on existing project, one JavaScript client side and the other Python server side. I told it to implement the server side one, it said ok, I tabbed away for a while, came to find the js implementation, checking the log Claude said “on second thought I think I’ll do the client side version instead”. Rarely do I throw an expletive bomb…
Edit: the main issue being called out is the lack of thinking, and the tendency to edit without researching first. Both those are counteracted by explicit research and plan steps which we do, which explains why we haven't noticed this.
I have found that Claude Opus 4.6 is a better reviewer than it is an implementer. I switch off between Claude/Opus and Codex/GPT-5.4 doing reviews and implementations, and invariably Codex ends up having to do multiple rounds of reviews and requesting fixes before Claude finally gets it right (and then I review). When it is the other way around (Codex impl, Claude review), it's usually just one round of fixes after t…
Hmm in my experience (I've done a lot of head-to-heads), Opus 4.6 is a weaker reviewer than GPT 5.4 xhigh. 5.4 xhigh gives very deep, very high-signal reviews and catches serious bugs much more reliably. I think it's possible you're observing Opus 4.6's higher baseline acceptance rate instead of GPT 5.4's higher implementation quality bar.
That analysis is pretty brutal. It's very disconcerting that they can sell access to a high quality model then just stealthily degrade it over time, effectively pulling the rug from under their customers.
I cancelled my Pro plan due to this two weeks ago. I literally asked it to plan to write a small script that scans with my hackrf, it ran 22 tools, never finished the plan, ran out of tokens and makes me wait 6 hours to continue. Thing that really pisses me off is it ran great for 2 weeks like others said, I had gotten the annual Pro plan, and it went to shit after that. Bait and switch at its finest.
Don't forget the 10x token cost cache eviction penalty you pay for resuming the session later.