A Controlled Study of Attention-Only Transformers · HackerPapers discussions

A Controlled Study of Attention-Only Transformers — HN submission

Tue, 11 Aug 2026 02:34:09 GMT

Attention-Only Transformers

3 points; 1 discussion reply on HN. Paper and source history. A submission is not an endorsement.

A Controlled Study of Attention-Only Transformers — HN submission

Mon, 10 Aug 2026 17:22:07 GMT

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

Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges 300-700 on…

537 points; 185 discussion replies on HN. Paper and source history. A submission is not an endorsement.

A Controlled Study of Attention-Only Transformers — HN submission

Wed, 22 Jul 2026 03:25:23 GMT

A Controlled Study of Attention-Only Transformers

2 points; 1 discussion reply on HN. Paper and source history. A submission is not an endorsement.