Dev runs a local model on Surface to boss around Codex and Claude agents
draginol · x · 2026-11-08
Developer draginol shares an experiment: running a local AI model on a Surface Laptop Ultra to orchestrate Codex and Claude coding agents in other workspaces. The next goal, he says, is testing whether the setup can deliver genuinely useful assistance—not building an arcade game, but helping users with tasks they'd previously have to do by hand.
More from coding & agent
- Dev benchmarks tiny LLMs on agent tasks: 9B passes 2/5, stepping up to 12B — draginol · 2026-11-08
- Engineer proposes CI/CD could become a handoff to a deployment agent — andreisavu · 2026-11-08
- Dev launches Local AI benchmark scoring models by hardware on agent tasks and speed — draginol · 2026-11-08
- Personal AI dot can now read inbox sign-in codes to log in on your behalf — Dimillian · 2026-11-08
- Dev plans eye-tracker to automatically feed agents visual context — johnlindquist · 2026-11-08
- Lattice: open-source 'Cursor for research papers' bundles Claude Code, Overleaf and citations in one app — minchoi · 2026-11-08