Replying to @karpathy
@karpathy's LLM Wiki is a Schelling point. I reached a similar solution from the perspective of a contributor / tinkerer with memxp. The root is persistent, agent managed markdown content. it can be adapted to solve YOUR issue - research, ops, doc preparation, whatever
Wow, this tweet went very viral! I wanted share a possibly slightly improved version of the tweet in an "idea file". The idea of the idea file is that in this era of LLM agents, there is less of a point/need of sharing the specific code/app, you just share the idea, then the other person's agent customizes & builds it for your specific needs. So here's the idea in a gist format: gist.github.com/karpathy/442… You can give this to your agent and it can build you your own LLM wiki and guide you on how to use it etc. It's intentionally kept a little bit abstract/vague because there are so many directions to take this in. And ofc, people can adjust the idea or contribute their own in the Discussion which is cool.
1
2
564
I built mine as a single Rust binary. agent reads/writes markdown, stores credentials, has a journal called Meditation.md that tracks errors. A cleanup process consolidates resolutions into rules so your agent repeats mistakes less often. ▎ github.com/pwchiefy/memxp
1
284
With a max plan for Claude / Codex, you can get a lot done using a system like this with 0 token anxiety - very little repetitive instruction for routine tasks
132
a very simple agentic memory system you can build yourself does this. cloudflare tunnel, vultr vps, tailscale, use Rust + Axum, google workspace cli for auth- you can get minority report style custom internal apps up with a few prompts - payments part is tricky
When I built menugen ~1 year ago, I observed that the hardest part by far was not the code itself, it was the plethora of services you have to assemble like IKEA furniture to make it real, the DevOps: services, payments, auth, database, security, domain names, etc... I am really looking forward to a day where I could simply tell my agent: "build menugen" (referencing the post) and it would just work. The whole thing up to the deployed web page. The agent would have to browse a number of services, read the docs, get all the api keys, make everything work, debug it in dev, and deploy to prod. This is the actually hard part, not the code itself. Or rather, the better way to think about it is that the entire DevOps lifecycle has to become code, in addition to the necessary sensors/actuators of the CLIs/APIs with agent-native ergonomics. And there should be no need to visit web pages, click buttons, or anything like that for the human. It's easy to state, it's now just barely technically possible and expected to work maybe, but it definitely requires from-scratch re-design, work and thought. Very exciting direction!
3
2
414
AI influencers are encouraging people to use their skill repos. some of them have telemetry wired in. maybe off by default... maybe not. Don't download anyone's skills pls. read the markdown, incorporate what makes sense.
4
346
next up is a telemetry audit of your favorite skill repos
1
133
My first piece in @BitcoinMagazine was published 🔥💪🏾 In the piece, I explore the current state of the #Bitcoin developer ecosystem in Africa, ways to improve it, and the road ahead 🌍⚡ bitcoinmagazine.com/technica…
75
137
9
558
2018: gave presentation to a central bank including this slide. The technical staff understood, higher ups are going CBDC, lol. PPL like Jack have focused on Bitcoin for years for good reason. Many backers of ETH etc muddy the waters & try to obfuscate why the world needs this.
4
5
46
We need more energy production to realize the potential of global human intelligence & reduce unnecessary hardship. bitcoin mining will dramatically mitigate the risk of developing renewable energy sources in 'frontier' markets. It is inevitable and unstoppable.
1
1
4
My copy from the 21st printing is old and moldy, but the ideas still resonate. Ordering another and re-reading
1
The global base money charts from @crypto_voices are fantastic. They should be a key standard reference when discussing Bitcoin's "TAM", or framing the "market cap" of Bitcoin
6
P. 54, the story of A.G. Gaston is told. Undertaker who became a successful lender. It covers the trajectory of numerous institutions, from the Freedman's Saving Bank and Trust (closed in 1874) , all the way to the collapse of ShoreBank in 2010, which was denied TARP Funding.
1
Carver (NY) did receive funding, but the original shareholders were diluted down to a 2% shareholding. P 265, the personally familiar reality of a higher cost basis (security etc) and lower fee income (less wealthy clients paying for high fee services) is discussed.
3) provide tax incentives for foreign VCs investing in Nigerian startups including those active in the Bitcoin economy & encourage those startups to keep reserves in BTC as well. Incentives should be solid if HQ stays in Nigeria.
1
2
5
The point is the problem is pretty easy to solve. Generate the asset people want to buy locally by mining with flared gas, attract foreign direct investment with incentives, make the local currency / bitcoin market deeper, backed by long term supply to reduce the forex outflows
2
6