Trending on Hacker News (123 points, 50 comments).

Genie 4 will roll out to developers and Google AI Ultra subscribers soon. (Genie 4 will roll out to developers and Google AI Ultra subscribers soon)

UC Berkeley’s LEANN vector index stores a pruned graph and recomputes embeddings at query time. It matches HNSW accuracy at 90% recall using 4 GB instead of 188 GB, at the cost of seconds-level search.

Liquid AI released LFM3, 6 open-weight 2B-class models for text, vision, audio, omni and decisions. LFM3-1.7B uses a tri-hybrid backbone, a 256K context window and fits in about 1 GB at 4-bit.

Mirendil released Fern 0.1, its first model, pretrained from scratch with a 10M-token context window.

vLLM Semantic Router released d3-ultra, a 27B open-weight multimodal decision model. It reads text, images and video once, then returns probabilities for every answer, scoring 87.2 on the team’s SR-Text test.

With OpenAI Daybreak, Check Point speeds up the research behind new security protections, enabling its analysts to turn vulnerability intelligence into customer defenses faster.

There are 57 million people worldwide living with dementia today. For the researchers working to help them, the obstacle isn’t a lack of effort — it’s too much data, too few experts to synthesize it and a pace of discove...

A Blog post by Ai2 on Hugging Face

Spine landmark detection from spinal X-ray is a key step for estimating spine deformation severity, for building biomechanical models, and for pre-operative planning.

Hybrid language models keep a key-value (KV) cache only in their few full-attention layers, but this cache is still the part of a prompt's state that grows with the prompt and that must be stored or moved to reuse it.

A large language model maintains conversational content in an external storage that is outside the model and grows as the dialogue continues.