V@B Gym playlist updated and ready to pump 😎 or pic your favourites and make your own🤩👇
open.spotify.com/playlist/7J…
Ethan Lin retweeted
During a five-course silent dinner at Rancho La Puerta, travel writer Lara Kramer learned to settle into the silence. cntraveler.com/story/if-a-si…
Ethan Lin retweeted
Introducing SpiderMonkey 🐒:
A "system 1" for coding agents.
Runs Jev in a loop your env and notifies agents of attention-worthy events.
npm install -g github:jayhack/spidermonkey
Why this works👇
Ethan Lin retweeted
Replying to @GOP_is_Gutless
Remove the entire school police force. Replace with competent officers who are no nonsense and remove students who can’t follow the rules.
Ethan Lin retweeted
For his debut TDS article, Hubert García Gordon presents an insightful answer to a thorny question: what does your pipeline output when the correct answer to a query is "nothing"? towardsdatascience.com/when-…
Ethan Lin retweeted
“Imagine there exists a really good movie about you. Animate the opening credits to this film with made-up names in any style you like. Return the sequence as an mp4.”
Claude Opus 5.5 (Extra)
Replying to @anime_shots
Ethan Lin retweeted
Where Thailand's laid-back feel meets some of the best places to stay in the country cntraveller.com/gallery/best…
Ethan Lin retweeted
hey, wdyk - meowbooks predicted this as well
MCP vs CLI for LLMs is the wrong discussion. People are debating at the wrong layer.
Both work incredibly well as long as they are run through a repl like environment that can persist state. The funny thing about CLI is that CLI tools are usually accessed through BASH which happens to be a repl with persistent state (the file system), therefore cli works much better than mcp. But this isn't even close to being an intrinsic property of MCP. Just means that we need better harnesses.
Right now the best repl for this are:
- bash + fs
- jupyter kernels
- codemode type repls, usually quickjs
LLMs understand the concept of forward evolving a system to solve a need very well. This comes from the agentic RL. They understand how to change the state of a codebase or acquire data from databases and then operate on it similarly to humans. But without an execution environment, they actually cannot do this properly.
My bet? Sometime soon someone will (or has already?) create a embeddable, sqlite style mini execution environment that parses bash, typescript, or tool calls into a common IL execution plan that's easy to security check before executing. And design this specifically for durable execution environments. Then we will just connect cli, mcp, webmcp, whatever to that and it accepts any of the input modalities as they can all be represented as each other.



































