Topic

#Codex

14 articles on Codex — news, releases, guides and analysis from the SourceFeed engine.

ChatGPT Comes to Linux Because Agents Made It Matter

Codex turned the desktop client from a chat wrapper into an agent console, and Linux is where those users live.

Tikal's 28-skill ADLC framework shows where team standards are headed — and how easy it is to overbuild.

The Apache-2.0 CLI drops agentic vulnerability scanning into any pipeline, with OpenAI's hosted models doing the thinking.

The Ona acquisition shows the real battleground is where agents execute, not where developers type.

OpenAI reverted GPT-5.6 Sol to 272k because the bigger window was silently double-billing long sessions.

Twenty independent Codex harnesses, Lean gates, and heavy tool sandboxes show how multi-agent work actually scales.

OpenAI now ships subagent tasks as ciphertext, extending opaque-blob design at a real cost to local debugging.

A local Go tool turns Claude Code and Codex session logs into 3D codebase replays you can scrub and audit.

Namespace collisions, missing workspace tools, and entitlement gaps are stalling agent runs before the model even gets a chance.

OpenAI's latest model family and desktop consolidation signal a transition from passive code generation to active, autonomous execution.

The consolidation of Codex and ChatGPT signals a shift from chat boxes to background desktop execution.

Telemetry reveals a sharp clustering of reasoning tokens at fixed boundaries, exposing how compute budgets silently degrade production outputs.

The benchmark bump is noise; the gated access, maintainer program and vendor channel are the real moves.

A global TRACE log sink in OpenAI's CLI can write hundreds of terabytes a year to a local SQLite file — and it's been festering for months.