Mmastodon TechnologySoftware first seen 6 h ago, last 6 h ago, peak #12
Developer finds LLM advice falls short on legacy Go code
Original: Alright folks, let's talk about Large Language Models. Specifically, my recent adventure trying to coerce one into givin
A developer has described an attempt to get a large language model to give genuinely actionable advice for refactoring a gnarly, old Go microservice. Writing about the experience, they note the gap between headlines claiming AI can optimize your code or find bugs and the practical results when dealing with messy, real-world legacy systems.
Why now: Ongoing debate about whether LLMs can reliably handle complex, real-world software engineering tasks.
Large language modelsGoHackaday
Evidence
- Alright folks, let's talk about Large Language Models. Specifically, my recent adventure trying to coerce one into giving me genuinely actionable advice for a gnarly, old Go microservice. We've all seen the headlines, right? "AI optimizes your code!" "Let an LLM find your… · hackaday@www.urbanmind.net · 3
API: https://socialmediatrends-api.osmike.com/v1/trends/1507092