Abacus AI's Jev bets on typed decisions: one forward pass to let agents think in parallel
bindureddy · x · 2026-09-17
Bindu Reddy, CEO of Abacus AI, argues the smartest idea this week isn't a bigger model but Jev: a small model that returns a decision instead of text—one forward pass, one probability per option, no tokens to wait for.
Her case: today's agents are painfully serial—pick a tool, wait; pick a branch, wait; retry or abort, wait. With typed decisions, an agent can fan out 50 sub-tasks and score them all at once, running planning, verification, and safety checks in parallel. The LLM stops narrating and starts scheduling.
Her thesis: chain of thought made agents deeper; typed decisions make them wider. Winning agents won't think harder about one step—they'll think about a thousand steps at the same time. The feature is shipping in the Abacus AI Agent.
Related event: TypeSafe exits stealth with decision model Jev and RLCD training method(76 posts)→
More from coding & agent
- Take: frontier LLMs are too slow and pricey — small models win workflows — TejasKumar_ · 2026-09-17
- Ahrefs doubles MCP units on all plans as MCP becomes its fastest-growing product — iannuttall · 2026-09-17
- Self-hosted enterprise AI agent aces 59/60 test questions, saves analysts 15 hours a week — alex_verem · 2026-09-17
- One prompt drives Blender end-to-end: MiniMax Design + MCP workflow demo — iamfakhrealam · 2026-09-17
- 4-AI relay writing experiment: ChatGPT drafts, Muse, Grok and Claude review in the open — AggressiveGift1532 · 2026-09-17
- Matt Pocock's agent skills repo outstars React in 6 months, talks AI coding education — mattpocockuk · 2026-09-17