Previously I called Claude a good junior programmer. Well, he's gotten a lot better since then! It's all over the news that Claude is so great at finding bugs that the US government banned use of it.
Also previously I talked about context window size.
Here's a brilliant analysis of context window size for programming tasks:
https://www.linkedin.com/pulse/out-context-halldor-fannar-9eeuf/
Halldor was my mentor for my best-received GDC talk. He's very analytical and it shows. It reminds me of Knuth who talked about his interest in counting things and that led to counting instruction usage which led to our modern concepts of simplified instruction sets.
Structuring code for most effective AI analysis could be interesting. I'm going to guess that the best thing to do (for now at least) is to fire up your agent and get it to summarize each module for you and the linkages between them. Then drop a single module in for modifications / debugging (which according to Halldor's analysis would be most well structured modules) and let it rip.
No comments:
Post a Comment