Ex-Gemini team's new lab Elorian launches visual reasoning model Glimpse, demoed on construction site safety
AndrewDai · x · 2026-10-21
Developer karankendre built SiteCheck, a tool that reviews construction CCTV footage using Glimpse, a new visual thinking model from Elorian — a lab founded by people behind Google's Gemini and Apple's MM-1. No manual danger zones needed: ask questions about a video and it returns timestamped hazards with reasons. In the demo, a fall-risk warning fires as a worker nears an unguarded opening and clears when he moves away, while the opening stays flagged. Footage is AI-generated; analysis uses real API calls.
Founder AndrewDai says models ace single images but fail on moving, angle-changing scenes; Glimpse is their first visual thinking model with frontier-competitive performance vs Astra on key visual reasoning benchmarks.
More from Models
- Musk: Grok Bot is the fastest-growing product he's ever seen, enterprise rollout in weeks — elonmusk · 2026-10-21
- Google: Gemini 4 Argon processed ~25 trillion tokens in first 72 hours — OfficialLoganK · 2026-10-21
- Leaked GPT-6.1-Sol reasoning traces show familiar GPT caveman CoT once spaces are restored — teortaxesTex · 2026-10-21
- Gemini 4 Scores Just 78% on FrontierMath Tier 4 as OpenAI Models Saturate It — haider1 · 2026-10-21
- Hamel Husain: public benchmark quality is abysmal — broken graders, sloppy harnesses — HamelHusain · 2026-10-21
- 163MB open-source speech model Bark 3.0 beats Whisper (57x bigger) and NVIDIA Parakeet (15x bigger) — Scobleizer · 2026-10-21