You say Claude, I too would prefer not to read reams of comments or an essay everytime I revise the plan in plan mode, but do you know if any other tools are better than it? I've never used Codex, but I remember Claude Web's natural conversational approach being a welcome sight compared to ChatGPT's overly-formatted listicles.
I switched to codex just before the Fable release. I got sick of Claude being lazy and not completing tasks. Imo, codex is currently a much better model, and it also seems to be technically stronger on the type of applied math and theory heavy programming I like to do.
My experience is Codex is much better but less creative. I use its agent through GitHub Copilot or the agent interface from JetBrains. Try the GPT Sol 5.6 on medium, it gives me good results
My experience with Codex is that it goes off to do its thing for 10-60 minutes and either nails it and comes back with everything done, or comes back with something that I almost can’t believe a near-SOTA model would think I wanted based on my prompt, or is of acceptable quality.
I think the tradeoff to Claude being so needy is that if you let models just run away with an inaccurate or incomplete understanding of what to do, they can go really far off the rails AND spend a lot of time/money doing it AND come back with something that literally doesn’t make sense or doesn’t work.
I prefer dealing with Claude’s reliable cringe to the aloof model that tries to play it cool when it needs help.
Probably just as well with how terrible Opus 4.8 has been for me lately. I'm sure it's a common thing to complain about the latest model being nerfed, but I've legitimately never experienced such a drastic cliff in Claude's quality and a rise in its hallucinations and basic comprehension errors since upgrading. The few days I experimented with Fable also weren't much more promising. Has anyone coined a term yet for the likelihood of newer models getting worse as the AI-generated content they get trained on starts to approach critical mass? If Anthropic isn't already thinking hard about a solution, they probably should be.
The whole Opus family has exactly the same cost structure [1]. Since Opus 5 is smarter, you can use lower effort levels (= less tokens) making it cheaper to run than 4.8.
