YC built AI versions of its partners on GLM-5.2, cutting latency 31% vs OpenAI
ycombinator · x · 2026-09-17
YC built AI versions of its partners for its Office Hour Simulator to help more founders work through startup ideas. After testing lightweight Gemini and OpenAI models, the team moved to GLM-5.2 on a dedicated Wafer endpoint.
YC compared that deployment against GPT-4.1 mini on OpenAI and Gemma 4 31B on Cerebras, evaluating answer quality, latency, and conversation duration: the Wafer setup delivered 31% lower average LLM latency than OpenAI and 44% lower than Cerebras, and users talked to YC's AI partners 2.5 minutes longer on average.
More from coding & agent
- A year-long blueprint for codifying your business with AI: one workflow, one skill at a time — evielync · 2026-09-17
- Managing 38 Codex agents from a phone: a full app built in 5 hours for under $30 — RichardsonDx · 2026-09-17
- Baseten launches Hosted Tools, bringing server-side web search to open models — baseten · 2026-09-17
- Dev demos fast app testing with typesafe's Jev and opencode browser automation — soumitrashukla9 · 2026-09-17
- Demo shows blazing-fast browser automation with typesafe's Jev and opencode CLI — soumitrashukla9 · 2026-09-17
- 68-Agent Build Cut $2K in API Costs by Keeping Long Context on One Orchestrator Only — TheMoonMidas · 2026-09-17