Comment by CamperBob2
16 days ago
I have a habit of getting GPT 5.5 to review everything Opus writes for me, and vice versa. The model in the reviewer role frequently finds things I overlooked myself. Occasionally in parts of the code I wrote.
No modern LLM has found any buffer overflow bugs in parts of my code that originated from another LLM. Again, though, they have found one or two that were my fault.
Having one clanker verify the output of another has minimal, almost non-existent, persuasive value as evidence.
Hopefully you're close enough to retirement age that it's a moot point for you.
If not, you're headed for a bad time, a major attitude adjustment, or (most likely) both.