Simular's neuro-symbolic agent runs 217x cheaper than Opus at 72% on OSWorld
xwang_lk · x · 2026-10-20
Simular CTO Jiachen Yang explained to ISMG how its computer-use agent Sai uses a neuro-symbolic hybrid: it learns a workflow once, then replays it with code instead of calling a frontier LLM at every step. On OSWorld, Sai was 217x cheaper than Opus alone at 72% success; savings kick in after the third run. A single LinkedIn recruiting task costs at least 50 cents with today's best models, making scale economically unjustifiable without workflow reuse.
More from coding & agent
- Factory adds Linear delegations, letting Droid agents run issues automatically — matanSF · 2026-10-21
- Agent memory, goals and emotion should be designed as one system, argues dev — mimi10v3 · 2026-10-21
- Meta launches Muse Wonder coding models with 1M context, $4/$20 per million tokens — AIatMeta · 2026-10-21
- CastWorkshop: open-source studio ties Ollama and ComfyUI into persistent AI characters — CastWorkshop · 2026-10-21
- Agents break in production for boring backend reasons, not model reasons — DayKnown1050 · 2026-10-21
- REA turns any site, app, or game into an RL environment via open-source AgentEnv — henloitsjoyce · 2026-10-21