Two-person team builds Glance, detecting targets across 256 images in 0.1s
bdsqlsz · x · 2026-11-22
A two-person team built Glance in three days, claiming 0.1s detection of precise targets across 256 images, with box accuracy reportedly beating Typesafe's official jev model, plus multi-box and semantic action-level recognition. A demo video is attached; no third-party verification.
More from Models
- Mathematicians confirm Claude-assisted proof of the Riemann hypothesis is correct — scientificamerican · 2026-11-22
- Anthropic releases FlashProve with Lean formalization, proving 400B MoE inference on one H100 — jiqizhixin · 2026-11-22
- Researcher argues LLM companies have no moat as the data-flywheel thesis falls apart — adam_karvonen · 2026-11-22
- Gemini users say Low thinking still burns 5-hour quotas on basic prompts, want a non-thinking option back — patg84 · 2026-11-22
- GPT-6.2 Sweeps Top of Game Dev Arena; Astra Costs $0.98 Per Generation — gdb · 2026-11-22
- Quant funds love reasoning models: 'not economically useful' is the wrong take — scaling01 · 2026-11-22