E2B

Headlines · 4

1. 3d
   LMSYS trains Qwen3 coding agent with asynchronous RL on AMD MI355X

   LMSYS Blog reports that its team trained Qwen3-30B-A3B-Instruct for coding-agent tasks using fully asynchronous agentic reinforcement learning on AMD Instinct MI355X, with Miles, SGLang, Megatron-LM, and Harbor. On a vendor-run, 100-task stratified subset of SWE-bench Verified, pass@1 rose from 7.3% to 27.5% after supervised fine-tuning and agentic RL. The system used separate inference and training nodes, capped trajectories at 64K tokens, and moved sandboxes to E2B cloud microVMs, supporting 384 concurrent trajectories and about 3,480 trajectories per hour.

   LMSYS Blog · 🔥 0
2. Oct 22
   Amp lets enterprises self-host orb sandboxes for its coding agent

   Amp Chronicle says users can now self-host orbs, supplying their own compute for Amp to turn into orbs. Running `amp orb provider` inside their infrastructure, the provider contacts Amp and waits for requests to spawn, pause or delete orbs, then dispatches those operations to a program the user supplies. Amp says the option is intended for enterprises with regulatory, internal-network or custom-hardware constraints and that most users probably shouldn't self-host; self-hosted orbs are free for individuals and teams, with enterprises charged standard orb pricing starting October 29.

   Amp Chronicle · 🔥 0
3. Oct 13
   Theory survey: security is top AI adoption barrier; Cloudflare leads agent sandboxes

   Writing up Theory's second annual AI in Practice Survey, fielded on 22 September 2026 with 455 senior technical builders, Tomasz Tunguz reports that security and governance rose from sixth to first among pain points in twelve months. 43% of respondents rate security and governance the most important pain point, with evals a distant second at 22%; only 10% say security tooling delivers the most value today, while 18% expect it to lead in future. Cost optimisation and model selection are now standard: 45% of teams route queries across models (23.7% on a router they trained, 21.5% on a proprietary one) while 54.7% send every query to a single model. Among the 259 teams whose agents write and execute code, 62% host sandboxes on Cloudflare, three times the closest competitor.

   Tomasz Tunguz · 🔥 0
4. Oct 7
   Omnigent open-source meta-harness orchestrates Claude Code, Codex and other agents

   Omnigent is an open-source AI agent framework and "meta-harness" that, per its project documentation, mixes Claude Code, Codex, Cursor, OpenCode, Hermes, Pi and user-defined YAML agents in the same session, with sessions that follow you between terminal, browser, phone and a macOS desktop app. The README also claims support for first-party API keys or Claude/ChatGPT subscriptions, cloud sandboxes such as Modal, Daytona, E2B and Kubernetes, and policies that pause for approval, cap spend or limit tool access, plus session sharing for teammates. The repository is currently listed on GitHub Trending for Python.

   GitHub Trending · Python · 🔥 0

Experience and discussion from the community

Share my E2B experienceAsk about E2B