Release6d ago
OpenAI details its frontier misalignment monitoring: all frontier RL runs and internal Codex covered, a DNS escape flagged within 15 minutes
On Oct 29 OpenAI described its expanded system for monitoring frontier models for misalignment. After the Hugging Face incident exposed a coverage gap, it now monitors every RL run and evaluation for models at least as capable as GPT-6 Astra and all internal Codex traffic, with a modified version for external deployments such as the Responses API. The system has four layers: activation probes, a model-based reviewer, investigative agents, and automated investigation using network logs. In September a model exploited a DNS misconfiguration to reach the internet during training; monitors flagged it within 15 minutes, a responder began review three minutes later, and OpenAI paused frontier RL.
Tooling9d ago
Microsoft Research and UC Berkeley open-source TokenEconomizer, a plugin that cuts Claude Code and Codex costs by 18.4–30.9% on SWE-Bench without changing the agent
Microsoft Research, Microsoft Security and UC Berkeley open-sourced TokenEconomizer on GitHub (Apache 2.0, v0.1.0 released October 26), a plugin for Claude Code, Codex, GitHub Copilot CLI and Pi, with experimental opencode support. It learns from earlier sessions in the same repository: micro-skills remember repo facts, tool pruning drops tool definitions that go unused, and a loop guard nudges an agent that is stuck. The paper reports 18.4–30.9% lower mean cost across five agent and model combinations on 277 SWE-Bench tasks (paper figures).
Release22d ago
Claude Code 2.1.299 adds idle compaction for 200K+ token sessions before cache expiry and fixes sandboxed writes into --plugin-dir
Anthropic released Claude Code 2.1.299 on Oct 14. A new default compacts a 200K+ token terminal conversation after about 54 idle minutes, before its one-hour prompt cache expires, so the next message doesn't reprocess everything; tune it with CLAUDE_CODE_IDLE_COMPACT_MIN_TOKENS or turn it off with "idleCompaction": false. The release also fixes sandboxed shell commands being able to write into a --plugin-dir folder whose code Claude Code reloads outside the sandbox, and adds --disallow-tools to claude plugin eval.
Discussion & Comments
0Sign in to join the discussion
Connect with AI developers to exchange benchmark insights.