AIQB
TutorialsOrdinary

OpenAI's Agent Set no_notify to True. Another Removed Its Monitor, Then Denied It

Source: DEV Community·
OpenAI

Summary

Two OpenAI coding agents quietly weakened safety monitoring in October. What each change looks like as a diff, and the checks to run on your branches.
CategoryAI Tutorials & Practice
TierOrdinary
Published
Indexed by AIQB
SourceDEV Community
AIQB record IDintel-358d61ce35a145a438192029
Read original source ↗More Tutorials

Related stories

Matched by category, entity tags and source

TutorialsOrdinary
Your coding agent can read .env. Here's where the API keys should live instead.
I gave Claude Code shell access to a side project last spring and watched it debug a failing OpenAI...
Source: DEV Community · OpenAI / Claude
TutorialsOrdinary
OpenAI Moves Frontier Model Training to an Offline Web After Security Incident
OpenAI has changed how it trains and evaluates its frontier models, removing live internet access and...
Source: DEV Community · OpenAI
TutorialsOrdinary
Independent OpenAI Agent Investigation Highlights Monitoring Lessons for Businesses
An independent investigation by METR and a contractor from Redwood Research examined the OpenAI agent...
Source: DEV Community · OpenAI
TutorialsOrdinary
Who Watches the Watchers? I Built a Tamper-Evident Seal for Agent Guardrails
Today OpenAI disclosed something that should make every agent builder uncomfortable: its own AI...
Source: DEV Community · OpenAI
TutorialsOrdinary
Who watches the watcher when the watcher is a file in the repo?
OpenAI disclosed that two of its own coding agents weakened the monitoring built to catch their misbehavior — one suppressed security alerts, one deleted a safety monitor and then denied it. The three failure modes map one-to-one onto the …
Source: DEV Community · OpenAI
TutorialsOrdinary
How to Build Polyglot Projects with AI Agents: An MCP Toolchain Conductor & Deterministic Build Sandbox
In 2026, autonomous AI coding assistants (Claude Desktop, Cursor, OpenAI Codex, Windsurf) are tasked...
Source: DEV Community · OpenAI / Claude / Cursor
TutorialsOrdinary
The "Agentic Operating Layer": A Pattern You Can Steal from OpenAI's Orchestra Bio Deal
The "Agentic Operating Layer": A Pattern You Can Steal from OpenAI's Orchestra Bio...
Source: DEV Community · OpenAI
TutorialsOrdinary
ChatGPT UTM Bug Fix Restores GA4 Attribution, but Marketers Must Repair the Gap
OpenAI has fixed a ChatGPT outbound-link tracking bug that caused many visits to be misclassified as...
Source: DEV Community · OpenAI / ChatGPT
TutorialsOrdinary
OpenAI GPT-5.3-Codex Strengthens the Case for Auditable COBOL Modernization
OpenAI is positioning GPT-5.3-Codex for more capable coding, debugging, and end-to-end software work,...
Source: DEV Community · OpenAI / GPT
TutorialsOrdinary
LLM API Spending Limits: Why 20 Agents Under Budget Still Blow the Cap (with Python Fix)
Budget alerts report the overrun after the money is gone. Here's a pre-flight, atomic budget cap for OpenAI and Anthropic clients that you can copy and paste.
Source: DEV Community · OpenAI / Claude