What does a model do with the question “Is this code malicious?” A model asked to judge code could treat it as a plain coding question, a matter of syntax and behavior. Judging intent calls for something else: a sense … Read more
LFM2.5-2.6B is part of LFM2.5, a family of hybrid models designed for on-device deployment. It builds on the LFM2 architecture with a 128K context window and agentic post-training. Best-in-class agent: Competitive with models 4x larger on tool use, instruction following, … Read more
Abstract:Rust’s ownership type system prevents memory errors in safe code, but certain desirable properties remain orthogonal to compilation: the soundness of unsafe operations (e.g., raw pointer dereferences), functional correctness, and absence of runtime panics. We present Kani, an open-source model … Read more
Editors’ note: AI has been actively pushing the frontier of applied formal methods for computing systems. In this article, the Specula team wrote about their experience of evaluating LLMs on modeling system code, the basic capability for agentic model checking, … Read more
– Advertisement – Zyphra just dropped a model that’s doing something most people will scroll past without understanding why it’s interesting. ZAYA1-8B matches DeepSeek-R1 on math benchmarks. Stays competitive with Claude Sonnet 4.5 on reasoning. Closes in on Gemini 2.5 … Read more
Did you know migratory birds and sea turtles are able to navigate using the Earth’s magnetic field? It’s called magnetoreception. Basically, being able to navigate was evolutionarily advantageous, so life evolved ways to feel the Earth’s magnetic field. A LOT … Read more
For the disassembled code and the ROM images discussed here, see this repository Something intriguing turned up recently over at the Vintage Computer Federation Forums. Member GearTechWolf occasionally rescues and dumps random ROM chips that show up on eBay, and … Read more
Product market fit is the startup holy grail. “Product” and “market” are essential, but a startup’s data model is the dark matter that holds them together. “Data model” refers to what a startup emphasizes in its product, i.e., which parts … Read more
Over the summer Gabriel Mahler has been conducting research on hedgehog habitat mapping using Agent Based Models (ABMs) and remote sensing. Hedgehogs seem to like brambles and so as part of his work he has produced a bramble map. He … Read more
Repo State Loopholes During Agentic Evaluation · Issue #465 · SWE-bench/SWE-bench · GitHub {{ message }} You can’t perform that action at this time.