Explore tools, prompts, skills, news and resources related to Codex.
Prompt works related to Codex
Latest articles, prompts, use cases and editorial content about Codex
OpenAI released GPT-6.2 Astra, a frontier tier for long-horizon professional work, and GPT-6.2 Sol, an everyday agentic tier, both available via API as gpt-6.2-astra and gpt-6.2-sol. Both offer a 1,050,000-token context...
OpenAI introduced GPT-6.2 Astra, a frontier model for demanding projects, and GPT-6.2 Sol, an efficient model for everyday work, both available through the API. Simon Willison shipped LLM 0.38 with support for the new mo...
Simon Willison, working with Prime Radiant, introduced an external sandbox pattern in which code executed by an agent runs inside a dedicated sandbox while the agent itself stays outside it. Three implementations were re...
An AWS Machine Learning Blog post presents a three-phase responsible AI maturity framework—governance foundation, pilot deployment, and evaluation and hardening—for platform and application teams building agentic AI. It...
WebArena-Pro is a new benchmark for web agents comprising 300 tasks across 20 self-hosted web applications in six domain categories. It extends evaluation beyond text and vision by treating audio and video as core observ...
The No AI Slop manifesto was introduced by Dex in the closing keynote at AIE CODE after cosignatures from conference speakers and is published at slopmanifesto.com. It is intended as a discussion tool for teams, and the...
AWS describes a deployable sample that routes coding-agent requests on Amazon Bedrock through LiteLLM and NVIDIA NeMo Switchyard. The sample offers Stage routing between a capable Claude model and a lower-cost Nemotron m...
Amazon Bedrock now provides zero-instrumentation cost attribution that traces every inference call to the IAM principal, enabling per-user cost tracking for AI coding and productivity tools. This post walks through confi...
OpenAI introduced ChatGPT Wallet, described as a secure way for agents in ChatGPT Work, Codex, and dots to complete purchases. The feature requires user approval and retains existing card protections. It is positioned as...
Folio is a context manager for long-horizon language agents that records linked turn notes, runtime event manifests, and source records, then folds older history into coarser views. Its fold exposes handles into the mani...
This AWS Machine Learning Blog post provides a detailed enterprise rollout guide for using OpenAI Codex with Amazon Bedrock for inference. It covers three access paths—Native AWS Access, AgentCore Gateway, and LLM Gatewa...
MBZUAI’s Institute of Foundation Models released PAN 2, an open world model that takes a scene and text action and simulates the outcome as video. It uses an LLM planner with a 29B MMDiT and a frozen Qwen3.5-9B text enco...
The paper introduces Embodied First Exam, a unified agent-native benchmark for coding agents that control robots. It covers 1,156 tasks across 35 suites and 47 robots, including new suites for spatial puzzles, dexterous...
A new arXiv paper presents two empirical studies estimating the energy and carbon footprint of agentic language-model systems. In iterative self-refinement on MATH, three refinement steps closed a 16-percentage-point acc...
The paper analyzes cost accumulation patterns across agent traces and argues that harness-side choices, while having minimal impact on task accuracy, strongly affect execution cost, with prior work reporting reductions u...
Anthropic released Claude Fable 5.2 and Mythos 5.2, claiming gains in coding, reasoning and vision, with Fable 5.2 topping the Artificial Analysis Intelligence Index at 65 and setting records on HLE-Diamond and FrontierC...