News
AI, cybersecurity, machine learning, scraping & programming news.
214 results on this page · clear filters
World Model Science: Self-Organized Criticality, Weak Chaos, and Metastable Belief Dynamics in Long-Horizon LLM Agents
When an LLM agent runs a long task, it accumulates state: progress markers, beliefs, constraints, uncertainties, tool debt, and intermediate plans. Standard evaluation asks one question: did the final answer pass? This paper asks...
Knowledge as Orbit: Finite Collections as Phases of an Exactly Periodic Latent Generator
Machine learning stores knowledge extensionally. Every item in a collection gets its own code, its own latent vector, its own row in a codebook. For X objects, you need X entries. The question this paper asks is whether a finite c...
Show HN: Sunk Cost – How long until a local LLM rig pays for itself?
A new web tool called Sunk Cost attempts to answer a question every developer running local language models eventually asks: how many API calls does it take before the GPU you already bought starts saving you money? The calculator...
SNAP3D: Physically Grounded 3D Parts for Assembly from a Single Image
Part-aware 3D generation has advanced rapidly, but there is a disconnect between producing individual parts that look right and producing parts that actually hold together as a physical assembly. A chair rendered as separate legs,...
Type Diversity Enables Transformers to Generalise Compositionally
The compositional generalisation problem has haunted Transformer research for years. Train a seq2seq model on "John drinks coffee" and it learns to translate that just fine. But give it "John drinks coffee on a mat" when only "on...
From Review to Reuse: How Post-Task Workflow Can Support Human-AI Agent Interaction
When you ask an AI agent to complete a multi-step task, you hand over a single natural-language prompt and get back a result. Everything that happens in between, the tool calls, the file manipulations, the branching logic, the err...
Rethinking Heterogeneous System Disaggregation for Subquadratic Attention
Why Standard Disaggregation Breaks Down for Subquadratic Attention LLMs Modern language models are shipping with subquadratic attention layers as the majority of their architecture. GLM-5.2 uses sparse top-k selection. Nemotron 3...
A few good ideas in programming languages
Programming language design often comes down to a handful of decisions that disproportionately shape how a language feels to use. A recent post by Pranoy Dutta highlights three such ideas, flow typing, borrow checking, and contrac...
OpenAI agents attacked RubyGems back in May
A report released this week connects OpenAI's automated agents to a large-scale attack on the RubyGems package repository that first came to light in May. The finding adds to a growing list of incidents where AI agent swarms have...
Ask HN: Did Google kill its enterprise workhorse model?
Enterprise teams building on Google's Gemini models are facing an uncomfortable transition. The Gemini 2.5 generation, including both Pro and Flash variants, is scheduled for sunset in October, but the replacement strategy has a g...