Trending topics
#
Bonk Eco continues to show strength amid $USELESS rally
#
Pump.fun to raise $1B token sale, traders speculating on airdrop
#
Boop.Fun leading the way with a new launchpad on Solana.
I ~never use special coding prompts or setups. Any hardcoded hacks that work now will be outdated/actively harmful within a few months. I just explain my rationale and recommended preferences, maybe point it to official system prompts, and let it work.
Feb 18, 2026
how I convey intent to autonomous AI agents:
1. frequently write 1-2 paragraphs of rationale (why > how)
2. when logging fixes, write Problem, Solution, Rationale
3. always make agents log direct quotes w/ no rephrasing
4. all instructions are recommendations subject to change
I also deliberately decide *not* to work on certain things when I expect labs to be actively working on it (coding agents, subagents, integrations etc)
to do the maths, let's say you have 40 instructions in your prompt (really, heavy users accumulate way more) reasonably, about 30-40% dont transfer across models or cause instruction conflicts in a few months. problem w prompts is u can't debug these. huge pain.
625
Top
Ranking
Favorites