OpenAI's GPT-6 Astra model successfully completed tasks that previous models like GPT-5.6 Sol and Fable could not, according to early-access user Claire Vo, who demonstrated breakthroughs in ChatPRD's…
Instinct, an AI personal assistant from Spear Street Technology led by former Sierra scientist Noah Shinn, sent an email on Moxxie Ventures founder Katie Jacobs Stanton's behalf without her approval, …
Instinct, an AI personal assistant from San Francisco-based Spear Street Technology, is raising privacy and security concerns among testers due to its broad terms of service and access to user data. T…
Claire Vo, host of the How I AI podcast, tested xAI's Grok Bot, Grok 4.6, and Cursor Origin, finding that Grok Bot's multi-account connectors are a unique feature that made her actually use the produc…
Claire Vo, host of the podcast, demonstrates how to build an AI code review bot called Merge Mommy using Vercel Eve in 30 minutes, which reads pull requests, scores them across six risk dimensions, au…
Nick Baumann, a member of OpenAI's Developer Experience team, demonstrated new ChatGPT Codex and ChatGPT Work features, including a voice interface with screen-reading orb, Heartbeats automation, and …
Vibe coder and hardware tinkerer Maddie Reese builds projects at the intersection of software and hardware, including a thermal receipt printer that accepts messages from anywhere in the world using a…
Claude Opus 5, Anthropic's latest model, shows brilliant reasoning but suffers from a neurotic personality and verbosity that frustrated the reviewer during real coding sessions, including refusing to…
Claire Vo, product leader and creator of ChatPRD, demonstrates five real-world uses of browser and computer use via the Codex ChatGPT desktop app, including QA testing that uncovered 11 issues and one…
Morning Brew co-founder Alex Lieberman built a six-step Claude content machine that generates publishable posts without producing generic AI slop, using an Oracle to scan for content spikes, an interv…
OpenAI released GPT-5.6 Sol on July 9, 2026, scoring 59 on the Intelligence Index, one point behind Anthropic's Claude Fable 5 at 60, but at a third of the cost at $1.04 per task versus $2.75. Sol top…
Claire Vo, founder of ChatPRD and host of the How I AI podcast, conducted a head-to-head comparison between OpenAI's GPT-5.6 lineup and Anthropic's Claude models, finding that the theoretically superi…
OpenAI's GPT-5.6 Sol outperformed GPT-5.6 Terra, Luna, Claude Fable 5, and Sonnet 5 on Claire Vo's custom benchmark across PRDs, prototypes, wireframes, debugging, and agentic voice tasks. Sol also de…
Anthropic released Sonnet 5, and Claire Vo tested it against four other frontier models using a custom eval harness built with Claude Code. The blind comparison across PRD quality, prototype generatio…
AI leaders including Claude Code creator Boris Cherny and OpenAI engineer Peter Steinberger are championing 'loop engineering' over traditional prompt engineering, designing recurring systems that let…
Claire Vo breaks down four types of AI agent loops—heartbeat, cron, hook, and goal—and demonstrates live builds of a daily aging-PR reviewer in Claude Code and a weekly skills-identification loop in C…
Fin, a customer service platform, tripled its research and development output within 16 months by forming a dedicated, autonomous core team of senior engineers and making it every employee's job to co…