On 4/17/2026 11:17 AM, Richard Biener via Gcc wrote:
I think it’s interesting to collect what people think they’d use LLMs for given
there’s wide enough corporate pressure to use LLMs more with the idea to
increase productivity and save money. With that in mind I for myself am still
in the early evaluation phase, but I can frame a few use cases I think I light
want to use LLMs (if they turn out capable of delivering):
- patch review pre-screening (does the message reflect what the patch does?)
- bug (pre-)analysis - while I’m good at that manually, creating N copies of
myself would be nice to reduce the time I spend daily on bug analysis/review
- feasibility checks - I have a large list of TODO items which my or may not
turn out useful (or even possible), if LLMs can do an early stage prototype
then it should be possible to evaluate those ideas (finally); in fact I have
picked one such item and am turning that into a benchmark for LLMs
I do not think LLMs will help me in actual coding. Maybe in monkey
refactorings, but there’s pre-LLM tools for that as well (never used them,
speaking to LLMs does sound more appealing than learning such tools)
Largely agreed. I've had limited success using LLMs to scribble out
python code for testing purposes and the like. I wouldn't use an LLM
for anything real.
One other area where I have had some success is throwing blobs of
assembly at an LLM to see if the LLM can discover missing identities
leading to potential optimizations. They tend to go off the rails
regularly, but they've been helpful in identifying interesting code for
deeper investigation.
Jeff
