alt Hacker NewsPrediction: as agentic code generation gets better, more and more code will be written JIT for it to be executed for security reasons. The engineer of the future is not only the one who uses agents to code, he uses agents to code each time "the" program is ran.
Replies
p-e-w • today at 11:11 AM
I doubt it. It seems far more likely that such code will be written just once by LLMs, but in a way that allows its claimed guarantees to be formally verified (e.g. in Lean). At that point there’s no need to JIT an implementation each time.
➕ show 1 reply
dakolli • today at 12:31 PM
No
What's there to gain security-wise? Nondeterministic generation & then execution of that code without proper verification seems to be the opposite of a good security posture.