Tenex pays AI engineers for output and builds an AI-native SDLC
Latent Space · rss · 2026-10-21
Latent Space podcast with Tenex's Alex Lieberman and CJ Hess: paying AI engineers by delivered work instead of hours, the MetaHarness system checking plans and decisions into Git so agents recover context, the Kill My SaaS experiment replacing a $43K/year tool with 72 AI-built submissions (human and AI judges disagreed), and a debate on whether vertical AI products survive frontier models.
More from coding & agent
- Pinekin to open-source: batch-sync conversation context across AI agent harnesses — yangyi · 2026-10-21
- CoEvo-RSI: NUS-led paper tackles brain-body mismatch in self-improving agents — Jiaqi Su · 2026-10-21
- Open-source Hermes video toolchain turns agent requests into finished MP4s — Teknium · 2026-10-21
- Zed tested 25 MCP tool search approaches, picked weighted BM25 over LLMs and embeddings — jobergum · 2026-10-21
- Argon excels as a video director, says Bindu Reddy, orchestrating SeeDance and ElevenLabs — bindureddy · 2026-10-21
- OmniGraph Open-Sourced: Git-Style Branches and Merges for AI Agent Memory — techNmak · 2026-10-21