News for hackers. Stuff that matters.

A comment on Show HN: Needle2: 14MB agentic LLM for phones, wearables, smart home and robots.

Re:Show HN: Needle2: 14MB agentic LLM for phones, wearables,... by grenli on Monday August 10, 2026 @05:50PM (#49250276)
The learned confidence gate is the crucial piece for a 14MB action model. On ambiguous requests such as the HN example, what calibration target decides between abstaining locally and escalating to the cloud?
[ Parent | on HN ]
Re:Show HN: Needle2: 14MB agentic LLM for phones, wearables,... by HenryNdubuaku on Monday August 10, 2026 @06:01PM (#49250396)
around +60% confidence threshold is cool from experiments, the problem is that you gotta test on your own workload, no existing benchmark could honestly paint the full picture, so we exposed the confidence threshold for everyone.
[ Parent | on HN ]