™High Taste Testers Ep. 1: OpenAI Shipped Everything. What Actually Works?
Latent Space pilots its new show "High Taste Testers": a 1h15m roundtable where six AI power users (Ben Davis, Ben Hylak, Dex Horthy, Allison Durham, Alex Volkov, swyx) discuss OpenAI DevDay releases, coding agents, personal assistants, and model choices, comparing their hands-on experience.
Key points Tap a time to jump
OpenAI DevDay: Dots, Spaces, and product execution
Great models versus great products
Agents versus assistants
Building a personal assistant with Pi
Decision models, Jev, and predictive interfaces
Model speed, writing quality, and subagents
Agent loops, forks, and context management
Haiku, Muse Spark, and Grok
Local models and coding benchmarks
Prompt injection and assistants taking action
Comments
More to watch
All →- 1:34:05All-In Podcast E293: CoreWeave Crash, AI Trade Cracks, Anthropic IPO Red Flags, Bill Gates Doomer
- 39:23No Priors with OpenAI President Greg Brockman: Cybersecurity, Drug Discovery, and the Math Results
- 1:49:56Why a 4-Billion-Point Kaggle Dataset Still Couldn't Beat Chance — Ian Quigley, Leash Bio (Latent Space)
- 28:04How to kill your SaaS: what we learned replacing a $43K/yr tool with AI agents
Latest news
All →- Oct 19MiniMax Launches M3.1 Flash: Nearly 3x Faster Inference, 70% Lower Cost
- Oct 19Replit Switches to OpenAI: ChatGPT Replaces Claude as Default Model
- Oct 19Anthropic Consults Law Firms on Negotiation Norms for AI Agents
- Oct 19Microsoft Pulls Out of Nscale's UK Data-Center Project Over Power Shortage
- Oct 19Tenstorrent Raises $1.5B at $6.2B Post-Money Valuation
- Oct 19GitHub Weekly Vol.2: 6 Projects Worth Your Time
Today
Oct 19 Monday- Brief
- GitHubGitHub Weekly Vol.2: 6 Projects Worth Your Time
Tested or read — weeklyAll →
- Quiz
- Call