I thought I was an OpenAI fanboy, but version 5.6 isn’t for me. Sol Ultra just keeps working and checking, and working and checking again, but it can’t even correct minor errors that aren’t a problem for 5.5 xhigh. I’ve rolled Codex back to 5.5 for now.
The problem is they nerfed 5.5 about a month ago. The change was immediately visible to me: context compacting started to happen about 3x as frequently.
I think 5.6 is still not even close to 5.5 xhigh pre-nerf.
Before the personal LLM craze you could easily get $400 Mac Minis from Apple's certified refurbished store. I bought two M2 Pros for that price and turned them into Asahi Linux CI machines.
Cheapest mac mini I could spec out on the apple store right now is about $750, which if you consider how much more capable its M4 processor is than the pi, is a pretty good deal tbh.
Speaking as someone who’s written a lot of post-mortems, they’re a really useful exercise, and demanding clients are the only reason they actually happen. If you don’t get any lessons out of your post-mortem process, you’re missing a huge opportunity to improve your services.
reply