News
AI, cybersecurity, machine learning, scraping & programming news.
Show HN: Open-Source DaiDocs now beats Graphify by 218x low tokens, 83% on LME
Open plain-text memory for AI, covering both history and code Your assistant's memory becomes files on your disk that you can open, grep and keep: .dai for documents and session history, .cai for a graph of your code. One of the m...
Microsoft Execution Containers: Policy-driven containment for AI agents
Microsoft Execution Containers Reach General Availability with Policy-Driven Agent Containment AI agents deliver significant productivity gains by operating across files, networks, and applications. This same capability creates se...
Decoupling Exploration from Optimization in RLVR
Reinforcement learning with verifiable rewards has become the dominant recipe for improving the reasoning abilities of language models. RLVR samples solutions to problems, scores each solution with a programmatic verifier, and shi...
Distilling Graph Geometry: Knowledge Gap from GNNs to MLPs
GNN-to-MLP distillation aims to retain the predictive accuracy of a message-passing teacher while deploying a graph-free MLP at inference. Existing methods mainly transfer node-wise predictions or use confidence-based reweighting,...
Why Forget-Only Unlearning Needs Memorization
Reinforcement learning with verifiable rewards has become the dominant recipe for improving the reasoning abilities of language models. RLVR samples solutions to problems, scores each solution with a programmatic verifier, and shi...
Your Prompt Should Do More: Effects of Retrieval Instructions in Embedding Models
Prompted embedding models have recently received increasing attention, particularly for retrieval, where detailed retrieval instructions are provided as part of the retrieval prompt. Several new datasets and studies have examined...
RECAST: Learning to Compute the Right Context through Adaptive Evidence Routing
Large language models are increasingly applied to tasks grounded in long, heterogeneous information sources. Conventional Retrieval-Augmented Generation (RAG) relies on fixed similarity-based retrieval, while agentic variants adap...
Validity Without Ground Truth: What Stated-Preference Economics Offers the Evaluation of Language Models
The problem of evaluating large language models becomes acute when the questions asked have no single correct answer. Policy worth, option selection, competing values—these are the everyday questions put to LLMs that resist tradit...
I built a ridiculous game to test decision models vs. 9 LLMs
A purpose-built decision model and nine foundation models faced the same twenty well-defined choices. The test measured how long each took and what it cost. The results show where each approach fits in a marketing stack. Why small...
When and why prototyping is still needed when working with AI agents
A local-first notes manager and issue tracker for agents and humans entered the author's workflow at a critical moment. Emm's core promise: users can start building with local agents without ever connecting to the cloud. That prom...