shaurya on X: "you have access to your optimal policy at all times. you just choose not to follow it. you can literally access it by asking “what should i be doing rn?”" / X
to view keyboard shortcuts, press question mark view keyboard shortcuts messages home explore notifications messages grok lists bookmarks communities premium profile more post haifa @haifazu post see new posts conversation shaurya @shauseth you have access to your optimal policy at all times. you just choose not to follow it. you can literally access it by asking “what should i be doing rn?” 1:56 pm · feb 21, 2023 · 184k views 28 247 1.3k 805 post your reply reply shaurya @shauseth · feb 21, 2023 when it’s time to rest the answer will be to stop thinking about random shit and rest. when’s it’s time to work the answer would be to work. same for planning or talking to people or leaving a place you don’t want to be in 1 5 193 6k shaurya @shauseth · feb 21, 2023 literally all of that boils down to asking one simple course correcting question. you can accomplish pretty much anything by continuously asking it 3 7 162 6.3k shaurya @shauseth · feb 21, 2023 this was pretty much the essence o
shaurya @shauseth you have access to your optimal policy at all times. you just choose not to follow it. you can literally access it by asking “what should i be doing rn?” 8:26 AM · Feb 21, 2023 676.4K Views 44 0 4 4 361 0 3 6 1 2.8K 0 2 . 8 K 1.8K 0 1 . 8 K Read 44 replies
Explore this link on the map →related reading
- GitHub - brexhq/prompt-engineering: Tips and tricks for working with Large Language Models like OpenAI's GPT-4. · GitHubgithub.com
- Stop asking people to maximize - Mark Xumarkxu.com
- Parsed | Custom, interpretable AI systems that continuously learnparsed.com
- Explore More: A Bag of Tricks to Keep Your Life on the Rails — LessWronglesswrong.com
- OpenAI | Research & Deploymentopenai.com
- GitHub - guidance-ai/guidance: A guidance language for controlling large language models. · GitHubgithub.com
- GitHub - affaan-m/ECC: The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond. · GitHubgithub.com
- GitHub - f/prompts.chat: f.k.a. Awesome ChatGPT Prompts. Share, discover, and collect prompts from the community. Free and open source — self-host for your organization with complete privacy. · GitHubgithub.com
- GitHub - jbhuang0604/awesome-tips · GitHubgithub.com
- GitHub - emcie-co/parlant: Build reliable customer-facing AI agents with Parlant: an interaction control harness optimized for controlled, consistent, and predictable LLM interactions. · GitHubgithub.com
- Direct Nash Optimization: Teaching Language Models to Self-Improve with General Preferencesarxiv.org
- The Shadow Question — LessWronglesswrong.com