It’s depressing how so many (pathetic) software devs are taking their hands off the steering wheel and letting LLMs do all the driving. If you think software quality was poor before LLMs, there’s no way it could have been worse than shit like this:

This became very apparent with GPT 5.6 Sol. It, too, was widely hailed to have near-Fable level intelligence. But I used it non-stop for a week and realized that they had mostly just dialed up the relentlessness meter to eleven, most likely via heavy RLHF.

Last week I gave it a small-sized auth ticket to work on, then stepped away. I came back later that afternoon and found that it had worked for 3+ hours and written 25,000+ lines of code. I skimmed over the code and it looked like a small fix followed by a massive number of additional checks around it, including static analysis tooling.

I gave it to another GPT 5.6 and said “check this code and see if it addresses the ticket”. It looked at it and said that 98% of it was garbage and should be thrown away (its own words). I then gave it to Fable, which said it was massively over-engineered. Fable’s theory was that the agent implemented the fix first, but then compacted and lost crucial context, forgot what the original task was about, and kept going. After many compaction cycles it was completely lost.