For the first half of 2025 (and earlier), I wasn’t impressed with the capabilities of LLM coding tools. Simple asks would result in code with errors or that didn’t accomplish the goal I’d specified. There were some points where I’d ask for something that was a one-shot small task, and it would be successful, but the quality would be low. The only real plus was speed – the models could crank out code dozens of times faster than I could write.

Continue Reading →