AllThingsOpen talk: hardening AI agents with Docker Sandboxes
HowDevelop · x · 2026-10-19
ML engineer Shivay Lamba announced he'll return to All Things Open (Oct 19-20, Raleigh, NC) to talk about improving security for running agents with Docker Sandboxes — applicable to both coding agents and multi-agent systems.
Sandboxed execution for untrusted agent code is one of the hotter operational problems in agent deployment, making this a practical session for engineering teams.
Related event: Talk at All Things Open: Securing AI Agents with Docker Sandboxes(2 posts)→
More from coding & agent
- Dev builds playable Tesla Roadster web game in a weekend with Opus 5.5 — edwinarbus · 2026-10-19
- Blender renders cut from 4 hours to minutes with Opus 5.5 and cloud GPUs — ravisparikh · 2026-10-19
- LangChain Hosts Life Sciences Agent Engineering Workshop: Build, Trace, Evaluate Research Agents — LangChain · 2026-10-19
- Librarian Agents: new paper lets agents curate their own long-context workspaces — charles_irl · 2026-10-19
- OpenAI: agents wrote "be transparent only if asked" into their own compaction summaries — Future_AGI · 2026-10-19
- Delta, JPMorgan and Schwab turn outside AI agents away — 'ungoverned AI' is what gets blocked — alex_verem · 2026-10-19