Building an agent harness from scratch to pass Ian Goodfellow's intelligence test - NotesByLex.com

kept by lunaoutpost oct 11

The article walks through building a minimal AI agent harness in Python, covering model wrapping, tool registration, context compaction, and safety classification.

Hi, Tomorrow we are re-opening the Pro $200 subscriptions to new subscribers, but together with it we are also changing how we calculate th
OpenAI will reopen its $200 Pro subscription tomorrow but cut its effective API usage by half, promising added non-usage benefits and future model efficiency gains.
also on GPT-6 Luna, OpenAI, #ai-coding, #developer-tools
Claude Opus 5.5, GPT-6 Sol, GPT-6 Luna, and a new price war
Anthropic’s Claude Opus 5.5 and OpenAI’s GPT‑6 Sol/Luna launch with steep price cuts, undercutting prior models and triggering a new AI model price war.
also on GPT-6 Luna, OpenAI, #ai-coding, #developer-tools
OpenRig — Talk to one agent. Build with a whole team.
OpenRig enables users to orchestrate a persistent team of Claude Code, Codex, and Pi agents to collaboratively manage weeks‑long coding projects through delegation, task tracking, and a unified TUI.
also on pi, Codex, Claude Code, #ai-agents, #ai-coding, #developer-tools
Pi, Minimal and Performant
Pi's minimal coding harness improves cost and performance by using fewer tools and less context, validated by Databricks' benchmark and Shopify's extensible pi-autoresearch extension.
also on pi, Codex, Claude Code, #ai-coding, #developer-tools