@elonmusk You have interest everywhere in the world. Why not just focus on US.
Try thid campaign in China. They will destriy your product with 90 percent price difference
Anthropic's engineer, Andrej Karpathy (ex-Tesla) just shared ASD-STE100 prompting system almost nobody uses
this is f*cking insane...
i applied it to my Opus 5.5 & Fable 5.5 motion prompt and it turned Claude into a premier motion studio.
send it to Claude, and thank me later. Then read the full roadmap with examples below.
Anthropic engineer released a prompt that turns Opus 5.5 & Fable 5.5 into a team of agents.
It’s f*cking unreal…
send it to Opus 5.5 & Fable 5.5, and thank me later. Then read the full roadmap with examples below.
Andrej Karpathy’s agent ideas reduce to one surprisingly simple pattern:
the model is not the agent. the loop is.
most people focus on making the LLM smarter.
but useful agents come from architecture:
observe → plan → execute → evaluate → update memory → repeat
each step has a job:
• observe → pull the right context
• plan → break the goal into actions
• execute → use tools and APIs
• evaluate → check what actually happened
• memory → keep what matters for the next run
the important part is that the system doesn’t stop after one answer.
every run creates new state → new feedback → better decisions on the next run.
that’s how you go from a chatbot to an agent that can handle long-running work and improve over time.
I put the full framework + primitives + evaluation layer into one page below ↓
Andrej Karpathy (ex-OpenAI, ex-Tesla) just released a prompt that turns Opus 5.5 into a harness that actually finishes the any job.
It's f*cking unreal...
send it to Opus 5.5, and thank me later. Then read the full guide for Opus 5.5 Harness Engineering.