ralph loop runs headless. i dislike headless sessions. i need to see and supervise agent work, possibly ask /btw questions of them, possibly pitch in ideas to the mix, etc etc.
@karpathy
-
SSH Mode for Distributed ML Development Workflow
By
–
yes, solid work trending in a good direction, but almost all my work is across like 20 different machines (my local, my claw machine, my gpu machines). possibly they could add ssh mode, a bit like VS Code does (for the same reasons).
-
Extracting VC Value: AI Coding Tools Tokenization Strategy
By
–
claude, codex, opencode, cursor, amp, …
just loop over them, optimally extracting VC money from all the mispriced subscriptions to turn them into tokens. -
Automating AI Agents to Continue Research Loops
By
–
sadly the agents do not want to loop forever. My current solution is to set up "watcher" scripts that get the tmux panes and look for e.g. "esc to interrupt", and send keys to whip if not present. Need an e.g.:
/fullauto you must continue your research!
(enables fully automatic -
Agent Command Center IDE for tmux Grid Management
By
–
tmux grids are awesome, but i feel a need to have a proper "agent command center" IDE for teams of them, which I could maximize per monitor. E.g. I want to see/hide toggle them, see if any are idle, pop open related tools (e.g. terminal), stats (usage), etc.
-
Building AI Agents: From Draft to Academic Emulation Framework
By
–
Yeah that's clearly the next part, e.g. my crappy first draft: https://
github.com/karpathy/agent
hub
…
have to emulate academia, not just a single researcher. but need more time to think through the details. -
Diverse Implementation Approaches CLI TUI Tool Use
By
–
very cool! I love to see all the different directions people take it in, here esp the CLI, TUI, tool use aspects.
-
Open Weights Versus Open Source: Infrastructure Challenges
By
–
Great read! Off in the jungle with no trails. Open weights != Open source not only because of the data but all the related infra for everything not inference.
-
Meta-Learning Approaches in Deep Learning: MAML Framework Discussion
By
–
Cool! I only had a quick sim earlier today but really enjoyed a number of ideas even unrelated to the claw part, esp around the skills system. In deep learning there were a number of meta learning approaches (Eg MAML paper in 2017) where the goal is to optimize for the model
-
From Chat to Code to Claw: AI Capability Evolution
By
–
First there was chat, then there was code, now there is claw. Ez