logoalt Hacker News

ghm2199 • today at 4:46 PM • 0 replies • view on HN

This. Yeah I think if one knows what they are doing, e.g. a seasoned developer. They can get a lot of mileage out of an LLM that is good at instruction following. which is why i like codex models. Astra may not be as good as Opus but the workhorse really is 6.2 sol. The best workhorse when it comes to the pareto frontier of `cost vs accuracy` or `inference time vs accuracy`.