Laude Institute's Slingshots Four ships 14 open-source projects on agent harnesses and open models
lateinteraction · x · 2026-10-21
Laude Institute unveiled the fourth Slingshots batch: 14 open-source projects from eight top institutions.
- Harnesses took center stage: Headlong (a microharness for persistent agents), ACE (self-improvement via context management), Exo (self-improving the harness itself), and dotagents (multi-agent setups)
- Innovation up and down the stack: kernels (Thunderkittens), inference (M), training (Marin), data (Atlantic-CC), evals (Decision Assistants), optimization (SkyDiscover), plus applications
- Also includes Pedagogical RL for teaching models to generate learnable reasoning trajectories
The batch bets on self-improving agent systems, maximally open models and training data, and research/decision applications.
More from coding & agent
- OpenAI Live API tip: control voice sessions from your backend via sideband WebSocket — pbbakkum · 2026-10-21
- OpenAI's MultiLangBench: PHP scores highest (91.3%) at building a database engine from scratch — ricklamers · 2026-10-21
- AI auto-optimization speeds genomics code 22x: extract_loci from 7.8s to 0.35s — jmschreiber91 · 2026-10-21
- UserProof lets Claude Code watch your user session recordings and boost conversion for $29/mo — doooyle · 2026-10-21
- dphnAI's distributed inference network served 32B DeepSeek tokens in 24h, ~6% of Venice's daily volume — Ronangmi · 2026-10-21
- Superconductor revamps agent picker spanning 8 coding agents with search and favorites — sergeykarayev · 2026-10-21