32:20
GPT-6 Astra blew away every one of my benchmarks
The How I AI channel documents hands-on benchmark testing and practical workflow demonstrations using GPT-6 Astra, OpenAI's new front...
Sort by: Newest Items
There are 10 items in this page
24:14
Build an AI code review agent with Vercel Eve (full tutorial)
Host Claire walks through building a fully functional AI-powered pull request review agent using Vercel Eve and OpenAI Codex, designe...
27:41
I let Codex control my browser so I don’t have to
This episode of How I AI focuses on practical browser and computer use with OpenAI's Codex (via the ChatGPT desktop app), walking thr...
36:41
GPT 5.6-Sol vs. Claude Fable: Why OpenAI’s new model crushes my benchmark
The How I AI channel puts OpenAI's newly released GPT-5.6 model family — Soul, Terra, and Luna — through a custom evaluation framewor...
51:52
How Gusto’s CTO uses Claude Code to ship like a startup
Eddie Kim, CTO and co-founder of Gusto, joins the How I AI podcast to recount how a five-person team — four engineers (including Kim)...
27:14
GLM 5.2 is SO GOOD (and almost free)
This video from the How I AI channel takes a close look at GLM 5.2, the latest open-weight model from Beijing-based startup Z.AI. The...
29:07
Loop engineering for beginners
The "How I AI" channel tackles one of the most-discussed but least-explained concepts in AI agent development: prompt loops. Inspired...
23:37
Why I love GPT-5.5 for hard problems
Claraveo, a product leader and early GPT 5.5 access tester, shares what she describes as two genuinely hard engineering problems that...
27:34
Claude Design is slow and I love it anyway (plus why I love ChatGPT Images 2.0)
Claire Valle, product leader and creator of the How I AI channel, offers a hands-on review of two recently released AI design tools:...
30:13
Claude Opus 4.6 vs GPT-5.3 Codex: Which is the better software engineer?
Host Claire Vo puts two of 2026's newest AI coding models through a practical head-to-head evaluation: OpenAI's GPT-5.3 Codex, delive...