Latent Space podcast: six power users compare what actually works in AI tools
altryne · x · 2026-10-17
Latent Space's new episode "High Taste Testers" convenes top AI power users including altryne, swyx, and benhylak for unfiltered takes on what actually works. Topics: OpenAI DevDay product execution, Dots vs Muse vs GrokBot vs Instinct, who's winning coding and personal assistants, and the gap between impressive AI capabilities and useful products.
Also covers Pi-powered personal agents, decision models, subagents, context management, prompt injection, and assistants that can spend money. The author notes the field moved so fast some takes were already obsolete by publish time.
Related event: Latent Space Rounds Up Six Power Users to Test OpenAI DevDay Products(3 posts)→
More from coding & agent
- Claude cut a 2.6-hour video export to 20 minutes — but only after being told to rebuild the server — byhewar · 2026-10-23
- 3 flight-booking rules my AI agent checks that I'd never do by hand — Efistoffeles · 2026-10-23
- OpenJet claims Qwen3.8-27B coding runs 1.9x faster than llama.cpp on one RTX 3090 — JeremyCMorgan · 2026-10-23
- Building an autonomous SEO agent in Hermes with three skills: programmatic pages, Keywords Everywhere, DataForSEO — EXM7777 · 2026-10-23
- Building a sports betting AI agent with onchain execution and human approval by default: architecture and lessons — Dry-Comfortable-2678 · 2026-10-23
- How do you audit AI agent decisions in regulated workflows? A field survey — Ok_Way_1993 · 2026-10-23