Adam Knight

Static analysis tends to find improbable edge cases. LLMs tend to trace code well, but optimize for token use and give up quick in broad searches. Together, find all the static issues and then have a model trace it to see if it could actually be an issue? Works great.

This echoes a pattern that’s worked well for me. Build something interactively with an agent then realize it’s going south, so extract a functional spec of what you wanted it to do and then build that out into a full technical design and hit Go.

Which just echoes all the best and most common advice when working with Agents: know what you want, write a complete prompt, and keep your hands on the wheel.

This looks like something fun to keep track of. Having near-instant responses from small models enables so many interesting things.

If things go this route for established, stable models then a lot of the general criticism over resource demands for GPU-heavy datacenters will … shift. I say shift because it won’t eliminate the angst some feel for what people have done with LLMs (“AI slop”) and they’ll latch on to something else. Treating silicon as a disposable product (and the attached board and supporting chips) would be a fair first target.