etherio
Fable is SOTA at CIFAR Speedrun: lessons on AI R&D automation
Agents are under-elicited: A case study in optimization tasks
Inverse Rubric Optimization: A testbed for agent science
Multi-agent systems as distributed software
For example, one spawns copies of the env with a PR and runs agents in the dev env to verify by running and demonstrating functionality and then comments on github
another one is just a generic software factory that spawns a bunch of agents to coordinate on some repo, others do a redteaming flow, etc...
Show HN: Druids – Build your own software factory
Hi HN!Druids (https://github.com/fulcrumresearch/druids) is an open-source library for structuring and running multi-agent coding workflows. Druids makes it easy to do this by abstracting away all the VM infrastructure, agent provisioning, and communication. You can watch our demo video here (https://www.youtube.com/watch?v=EVJqW-tvSy4) to see what it looks like.At a high level:- Users can...
Show HN: Druids – coordinate and deploy coding agents across machines
More Is Different for Intelligence
Show HN: Orpheus – PR review that runs the code
2025 Letter
Personalization Requires Data
Show HN: Lunette – auditing agents for evals and environments
Dense reconstruction is the scaffold of machine learning
this kind of tool is especially useful in longer running tasks to enforce your intent without having to check in on your agent all the time
Show HN: Quibbler – A critic for your coding agent that learns what you want
Show HN: Orchestra – an interface to usefully run coding agents in parallel
Show HN: Automated monitoring and orchestration of coding agents
AI Agents and Painted Facades
The machine has no mouth and it must scream
2024 in Review
Aphantasia (and how not to do math in your head)
I'm currently exploring how AI/Natural Language Processing can automatically organize personal knowledge and notes by tagging and linking ideas / content together [0], removing the friction of organization to help you find new connections and ideas.
If you're interested in this domain, I'd love to talk to you!