Default avatar
npub1dqn7...2wpa
npub1dqn7...2wpa
tl;dr: - Prompt engineering is very much alive. - “Few-shot prompting” can improve accuracy from 0% to 90%. - Role prompting (e.g. “You are a math professor. . .”) is largely ineffective. - Advanced techniques like decomposition and self-criticism unlock better performance. - Context (“additional information”) is underrated—and massively impactful. - Real leverage comes from crafting high-performing prompts inside products. These prompts are used at scale, run millions of times, and must be hardened and optimized like production code.
Musk wasn’t remotely aware of the “woke virus” during Obama’s two terms. No elites from either party were aware of the “globalization virus” as a bad thing for democracy in the 3 decades since the fall of the Berlin Wall. Even Peter Thiel came late to partial recognition of the tripple evils of globalization, social-justice and environmentalism. All three are necessary evils carried to excesses. There is only one philosopher in the West, or the entire world, that I know of who had perceptions and misgivings about downsides of all three, 3 decades ago. Who was that philosopher?
🤔 discuss “One of the biggest mistakes you can make in your career is investing your time in building up an anonymous identity instead of your own real name and face.”
You’re all so idealistic, naive, and stupid. Short-term thinkers, non-strategic. You all might as well be D’s. I look forward to real leadership in this community.