alt Hacker NewsI’m just surprised this works at all. When I was building AI automations for a startup in January, even 1,000 word system prompts would cause the model to start losing track of some of the rules. You could even have something simple like “never do X” and it would still sometimes do X.
Replies
dataviz1000 • yesterday at 1:48 PM
I created a test evaluation (they friggen' stole the word harness) that runs a changed prompt comparing success pass / fail, the number of tokens and time of any change. It is an easy thing to do. The best part is I set up an orchestration pattern where one agent iterations updating the target agent prompts. Not only can it evaluate the outcome after the changes, it can update and rerun self-healing and fixing itself.
Two things; the model and runtime matters a lot, smaller/quantized models are basically useless at strict instruction following, compared to SOTA models. The second thing is that "never do X" doesn't work that well, if you want it to "never do X" you need to adjust the harness and/or steer it with "positive prompting" instead. Don't do "Never use uppercase" but instead do "Always use lowercase only", as a silly example, you'll get a lot better results. If you've trained dogs ("positive reinforcement training") before, this will come easier to you.