pull down to refresh

106 sats \ 1 reply \ @SimpleStacker 14 Mar \ parent \ on: Meta's $70m efforts lobbying for age-verification laws Politics_And_Law

I might do a write up of my process. It was an iterative loop along these lines:

  1. Start a new session (no memory)
  2. Upload current version of model and (incomplete) proof
  3. Ask it to complete the proof
  4. Evaluate the AI's proof completion
  5. Poke the AI on parts that I found incorrect or dissatisfying
  6. Iterate within the chat on why that part was hard or dissatisfying
    • If simply a mistake by the AI, fix it
    • If model setup is genuinely problematic, revise assumptions
  7. Update the model with new assumptions as appropriate
  8. Go to step 1
write
compose
6 sats \ 0 replies \ @optimism 14 Mar

For step 5, is there a way to make it come to that conclusion?

Not sure if it's 100% comparable but maybe there's something close to it: if I find a thing in code, instead of "arguing" or "pressing" I just say: write a test around <xyz> in case there are any issues and then it 90% of the time finds its own error.

reply