TWIML podcast: TypeSafe's Jev model bets on machine-native intelligence over LLMs
samcharrington · x · 2026-10-10
TWIML episode 779 features Diogo Almeida, co-founder and CEO of TypeSafe, on their newly released model Jev and the idea of "machine-native intelligence."
Key points:
- Text-optimized LLMs are poorly suited to many real-world automation decisions
- Jev differs from classifiers and LLM approaches, using RL from calibrated decisions (RLCD), with calibration and reliability as the core of AI as a software primitive
- Almeida argues AI systems should be more engineered — models + code working together — rather than one model doing everything
- How Jev-like models could reshape agents, tool use, and AI software architecture
A deep interview on what models should look like when built for software, not chat.
Related event: TypeSafe's Fast Decision Model Jev Goes Viral as OpenAI Chases(7 posts)→
More from coding & agent
- Indie dev builds a GT5-grade browser racing sim in ThreeJS, tuned to IMSA GT3 rulebook — AIandDesign · 2026-10-10
- Agent-built system hits 2,242 tok/s on AMD MI300As, 2.33× faster than SGLang in 105 hours — bariskasikci · 2026-10-10
- Seroter's Daily Reads: Agent-Friendly APIs, LLM Judges, and Ambient Quality Agents — rseroter · 2026-10-10
- Steve Yegge: Claude just reads the binary when it wants to know how closed-source Rex works — Steve_Yegge · 2026-10-10
- YC hosts an agent-first hackathon in San Francisco, sponsored by Supabase — ycombinator · 2026-10-10
- Running a fleet of long-horizon LLM agents: 9 keep-alive patterns and 5 unsolved problems — milkygirl21 · 2026-10-10