Engineering
TurboQuant Quantization Explained
TurboQuant is a vector-embedding compression technique that applies a random orthogonal rotation to embedding coordinates, then maps the rotated values…
Engineering
Per-tensor layout maps for GGUF quantization
A Hugging Face contributor describes a data-driven quantization scheme for GGUF models that empirically measures per-tensor sensitivity rather than relying…
Engineering
From Parameters to Answers: How LLMs Retrieve and Use Their Internal Knowledge
The paper studies how large language models retrieve and use internal knowledge by performing layerwise interventions on hidden states across…
Engineering
When Agents Disagree: Bayesian Backward Reasoning as a Label-Free Anchor for Multi-Agent Collective Decision-Making
The paper proposes a Bayesian backward-reasoning method for aggregating decisions from multiple LLM agents, constructing reverse posteriors via explicit likelihood…
Engineering
Beyond Confidence: Stability-Aware Test-Time Adaptation for LLM Reasoning
The paper introduces TASCO, a test-time adaptation framework that improves LLM reasoning by optimizing lightweight task-level prefixes while keeping the…
Engineering
A Unified Per-Token Gating Family for On-Policy Distillation: FKL/RKL Mixing with Multi-Channel and Bias Coefficients
The paper proposes a unified four-coefficient parameterization for on-policy knowledge distillation that generalizes existing per-token gating methods by combining forward…
Engineering
Memory Compression for High-Fanout Agent Sandboxes
Researchers introduce AgentZip, a memory compression system for AI-agent sandboxes that exploits redundancy across sandbox instances and between sandboxes and…
News
US Agencies Accuse Six Chinese AI Companies of Systematically Copying American Models
A joint FBI, NSA, and CISA advisory published in early September 2026 accuses six Chinese AI companies — DeepSeek, Moonshot…
News
Salesforce Launches Seven Named Agentforce AI Agents
Salesforce unveiled a suite of seven named AI agents — Casey, Paige, Carter, Hunter, Marshall, Piper, and Fin — each…
News
Hundreds of AI Agents Used to Breach 395 Organizations via PaperCut Flaws
A suspected Russian-speaking threat actor deployed hundreds of AI agents built on OpenAI’s Codex and a DeepSeek model to exploit…
News
Federal Judge Rules Pentagon’s Anthropic Blacklist Was Illegal
A federal judge ruled that the Pentagon acted illegally when it designated Anthropic a ‘supply chain risk’ in February 2026.…
Opinions
We Must Pace the Frontier
In a roughly 3,800-word essay published September 12, 2026, Anthropic CEO Dario Amodei argues that AI companies should deliberately slow…