Khanh Nguyen

Everything will be agent-first.

Decoupling sleep and dreaming for continual learning seems intresting. Going to implement some of the on the fly RL and distillation to see if it holds up. In practice, I think we're missing a cleverly designed memory layer though, nobody's cracked that yet. arxiv.org/abs/2606.03979

Hope people aren’t tired of the “just use Postgres” meme yet (surely not @BenjDicken), but Postgres can be your filesystem too.   Today I’m launching sql-fs: a persistent bash sandbox over HTTP and MCP, backed by Postgres.   Most agent sandboxes still spin up VMs: cold start time, per-minute billing, and costs that climb when you run lots of sessions. I went a different way. just-bash is the virtual bash runtime. I built the distributed and persistent layer around it, which is a Postgres-backed virtual FS with consistency across replicas and in-process caching, so sandboxes are cheap to create, quick to resume, and durable across process restarts.   What you get: • Filesystem state in your Postgres (RLS per sandbox) • Content-addressable blobs (dedup across sandboxes) • 3 layers of caching and locking for distributed exec • Path and content caches so stat/read don’t hammer the DB every time   Repo: github.com/Hazzng/sql-fs   I also wrote a longer blog post (see reply below) on how it works in depth. Have a read if you’re curious about the distributed design to achieve strong consistency :)   PS: thanks to @cramforce for the amazing just-bash!

First video up! I'm a research student from Australia, and I want to build a little circle of people learning this stuff seriously and pushing each other to get better. Sharing my journey as I go, starting with visiting DETR. If that's you, join in :) youtube.com/watch?v=RpgSdr…

PhD finished ✅

Slides from my talk at @ai_ucl today on "Controlling Diffusion Models: Assorted Approaches" docs.google.com/presentation/d…

Advice this advice that. JUST DO THE WORK