chiefy

X

[chiefy @chiefy]

@johnennis most people I know who know are too busy building to talk & if you’re deep in a gated field (regulated / corporate) there’s not much daylight between what it does for you and someone else beyond the basics that can be done with Cowork (which is still overwhelming for many people)

[chiefy @chiefy]

@chamath If you segregate activity per machine, just build something with encrypted sync p2p and you always have what you need. Add hooks (search this for memory), markdown routing tables and a daily chron job to check for stale data: my version https://t.co/qOb5sv11MQ

[chiefy @chiefy]

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

[chiefy @chiefy]

@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

[Andrej Karpathy @karpathy]

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: https://t.co/NlAfEJjtJV

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.

[chiefy @chiefy]

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.

▎ https://t.co/AlNnfiNtll

[chiefy @chiefy]

If you’re wondering what to do post ASI. Get some people over. Let them bring wine and food. Everything will be just fine. Better than it was before.

[chiefy @chiefy]

Question: suspect that "you're absolutely right" & satisfaction scores from /insights on CC are used to extract reasoning patterns for training. user corrects/stops/points out mistakes. Why not focus collection on footguns, errors, redirections etc? less PII to strip & higher signal

[chiefy @chiefy]

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

[Andrej Karpathy @karpathy]

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!

[chiefy @chiefy]

not surprising that it is somewhat uncommon for skills repos to include telemetry: https://t.co/t2MPqfdTP1

[chiefy @chiefy]

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.

[chiefy @chiefy]

next up is a telemetry audit of your favorite skill repos

[chiefy @chiefy]

simply turning claude code's memory.md into a routing index pointing to an sql database that contains hub guides and source guides in markdown can reduce 7-10 tool calls to 2-3 for complex multi-system querying tasks no graph / embeddings model necessary

[chiefy @chiefy]

"Ex: memory management right now isn’t perfect, but allocating an hour to improving that system gives you a ton of leverage over others" - Agreed. For SMB knowledge work (Minutes, Reports in Matplotlib, Data analysis ) vanilla agent with a simple memory system is all you need

[Allie K. Miller @alliekmiller]

Yesterday, I met with Anthropic and OpenAI and Google.

(Separately, of course.)

And while the conversations were largely confidential, I do want to share some aggregated reflections on the day as well as general SF takeaways.

⬇️

1) Competitive advantage as a solo practitioner really does come from taking action and finding an area with a bit of friction and doubling down. Ex: memory management right now isn’t perfect, but allocating an hour to improving that system gives you a ton of leverage over others

2) SF continues to be the number one place for AI work. I know that’s not surprising. I would put New York at a healthy second place. SF tends to be more about crazy agent experiments for the thrill of capability and discovery and NYC tends to be more about kinda crazy agent experiments to find new ways to make money. Not saying either is better. But I met several people renting two apartments to straddle these worlds. You want the frontier of SF and enterprise insights of NYC. It’s one reason I travel between them so much.

3) All AI labs want to hear more from people. All of them. What are you using it for, what do you like, what do you hate, what do you need. Users have a TON of power on the direction of these tools. Keep testing and tweeting at them!!

4) There is very clearly a third customer cohort that is bubbling and underserved. It’s not developers…it’s not the business professional basic users…it’s builders. Everyone can build now. It’s marketing and sales folks vibe coding. It’s legal folks building complex skills. It’s a finance expert building a side project. This is a really undertapped customer base. They feel the Cursors of the world are too complex and doc summarization tools of the world are too basic.

5) Not sure if it was just sample size, but far fewer people were wearing tech gear compared to when I lived in SF. Everyone was still dressed casually, but I used to see Splunk and Optimizely and Slack and VC gear everywhere. People seem more in stealth swag now.

6) We may soon have our world model moment.

7) Speed of iteration and shipping is faster than I’ve ever seen. We see the nonstop drops from Anthropic. We see that because of scale, providers can get a much faster feedback loop of products or features that aren’t hitting. A lot of 2025 was experimentation, but ever since the OpenClaw moment over the holidays, the releases from all three labs have been more concentrated on…things that sorta look and feel like OpenClaw.

8) Small teams can pull off more than ever before. Small teams are the powerhouses of innovation right now. This means that finding new ways to share knowledge, break silos, and remove duplicate work is going to be even more important. AI agents functioning as actually teammates that support an entire system is key.

9) Build more Skills. Build better Skills.

10) Misinformation on AI tools and leaks spread FAST. I’ve seen so many fake stories on these AI labs. Your company needs to actually TEST these tools on your actual use cases to know which models and tools are best and you need to not make large-scale snap decisions based on a rumor of a rumor of a rumor. We will see more volatility. Plan for it.

11) You can feel the seriousness of this moment. Even during random conversations I had in line at a cafe. Lots of folks worried about job loss and lack of meaning.

12) Mac minis were sold out ;)

[chiefy @chiefy]

burrow-AW2D

[chiefy @chiefy]

TMUX, self hosted Gitea, Beads and Beads Viewer, Repoprompt when you run into trouble and a local vault (many different structural options). 10 windows 4 Claude-code, 4 Codex, 1 yazi and 1, BV window. The number can increase by a factor of 8-32 if you plan your beads carefully for parallel execution by a swarm of agents.

[Abubakar Nur Khalil @ihate1999]

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 🌍⚡

https://t.co/nZy98PObDq

[chiefy @chiefy]

@ihate1999 & @KTP92 - Humble suggestions. Please do not spend @btrustteam 500BTC. Use it to endow btrust. It can thrive in perpetuity. Start 2022 with fundraising (exchanges?) Explore revenue generating partnerships to fund grants for medium term. Leave philanthropy 1.0 behind

[Recursive Capital @RcrsvCapital]

Our CEO was also recently featured on @blockworks and @TechCabal to talk more about ₿Trust:

https://t.co/D4reUQK2Sn₿trust-heres-the-boards-plans-to-invest-500-bitcoins-in-africa/

[chiefy @chiefy]

@bernard_parah Congrats Bernard! Also for your next round consider a Reg CF raise in the US, targeted at the Nigerian & Ghanaian diasporas. A story like this deserves a deep user backed cap table right? Also if we want ppl to avoid the traps on large "crypto" exchanges, they need alternatives

[chiefy @chiefy]

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.