In a solo episode of the How I AI podcast, Claire tested Grok Bot, Cursor Origin, and Grok 4.6, finding that Grok Bot's multi-account connectors solve a problem other agent platforms ignore, while Cur…
Claire built an AI agent that reviews pull requests, scores their risk, auto-approves the safest ones, and sends questionable changes to Slack, all in a single Codex session using Vercel Eve. The agen…
OpenAI's Nick Baumann demonstrated advanced ChatGPT, Codex, and Voice workflows on the 'How I AI' podcast, showing how Codex can operate a computer via voice, fork threads for parallel tasks, and auto…
Claire demonstrates how she uses Codex for browser and computer use, including testing apps, managing LinkedIn, and controlling an iPhone via screen mirroring, in a new episode of How I AI. She found …
Z.ai's open-weight model GLM-5.2 is emerging as a cost-effective alternative to proprietary AI code assistants like Opus, offering a million-token context window and advanced features. In testing, it …
Anthropic released Claude Fable 5, its first Mythos-class model, which achieves 80% on SWBench Pro but costs $10 per million input tokens and $50 per million output tokens. The model excels at vision …
Claire, host of the podcast "How I AI," used Google Flow and Gemini Omni to clone herself into an AI avatar and produce a full one-minute hype video in approximately 15 minutes, demonstrating how AI v…
Anthropic unveiled five major updates at its "Code with Claude" event, including scheduled AI routines, outcome-based agent grading, multi-agent orchestration, and a new "Dreams" memory system for lon…