City University of Hong Kong
AI overview
Sign in and the AI will write an overview from our coverage.
Headlines · 2
- Taste-Bench: AI agents pick the better long-horizon path only ~60% of the time
Researchers from Microsoft and City University of Hong Kong built Taste-Bench, which tests an agent's "taste" in long-running tasks by freezing a run at a "decision fork," hiding later work and asking a model to choose between two diverging paths. The benchmark has 502 binary questions drawn from thousands of scored agent runs on coding and AI research tasks, including SWE-bench Pro and METR's MALT transcripts. Across 14 models, GPT-5.6 Sol led with 59.7% and GPT-5.5 followed at 59.5%, while average accuracy fell to 21%, near random, when the deciding clue appeared only after extensive later work. The team also distilled a teacher's judgment into a Qwen3.6-27B student, lifting accuracy on unseen tasks from 30% to 47.9% and raising success on 41 held-out SWE-bench Pro tasks from 14.6% to 33.7% when its advice was added to the task context. The benchmark and code are publicly available.
The Decoder · 🔥 0 - Huawei's Hubble backs Shita Robotics' color-changing photonic-crystal e-skin angel round
On October 13, Shenzhen-based Shita Robotics closed an angel round whose investors include Huawei's Hubble investment arm, a fund under Shenzhen Gaoxin Investment, and Gaoxuan Investment, with Duowei Capital as exclusive financial adviser; the report did not disclose the amount raised. Founded by Zhang Wei, born in 1998, the roughly 50-person team (average age about 23) is combining flexible photonic crystals, notably cholesteric liquid-crystal elastomers, with a flexible TFT photosensor array to develop an e-skin under 1 mm thick with a sensing density above 10,000 points/cm² — figures that come from the company. Shita is also developing an add-on "tactile cerebellum" model meant to work alongside VLA-style models, and says internal tests on tasks such as erasing a blackboard or inserting a peg showed success rates rising by up to nearly 100%, a claim not independently verified.
量子位（原生 RSS） · 🔥 0
Experience and discussion from the community
Share my City University of Hong Kong experienceAsk about City University of Hong Kong
Nobody has shared their experience with City University of Hong Kong yet.