the medical school taught you to believe that the world is rigid and can't bend to your will, forgetting that penicillin and x-ray was found "accidentally"
I’m significantly older than you. I started coding in the late 60s. My current strategy is to not read any of the code written by my agents. That’s the only way I can take advantage of their productivity. What I do instead is to surround the agents with extreme constraints. Unit tests, gherkin tests, QA procedures, quality metrics, mutation testing, test coverage, and a plethora of others. In the end, I have very high confidence in the code they produce because they’ve had to run the gauntlet of all of my constraints and tests.
jev:
- removes probability from invalid tokens
other models:
- unable to handle probability -> will show signs of confusion
- we can't just remove the signs of confusion
@yacineMTB Hashimoto's post yesterday p much nailed it. Don't gotta read the code necessarily, but you need to understand how shit works before you commit to shipping to production. This essentially has not changed from the pre-LLM world lol