Hello Hugo and others; yours is a good list of when to use an LLM, except I take issue with one part; overall someone™ should eventually find free language data and put together a plain LLM data Guix package as a component for guix refresh.
Hugo Buddelmeijer via <[email protected]> writes: > This small list is just scratching the surface, but these are things > I'd like to do already now: > > - Agents help with learning and gaining understanding, for example an > unknown code base. > > - Agents often (not always) produce much better code. Especially for > simple things, so we as humans can focus on the more complex / > higher level things. > > - Agents can check human written code. They can catch many minor > problems, so the humans can focus on the big problems (assuming the > LLM doesn't catch those also). I do not believe that the LLM check code well. Static analysis tools do this, cheaply and low-cost; some are free and in Guix. The LLM just articulates what static analysis has found, and proposes fixes. > - Agents are so much faster for simple things, like writing patches > for broken packages. This frees up human time for more complex > things. Regards, Florian
