llm
30 articles about llm in AI news
BayesBench: LLMs Match Bayesian Posteriors But Fail Downstream Prediction
BayesBench tests 7 LLMs on multi-turn Bayesian reasoning. Scaling improves latent inference but not prediction, exposing a critical gap for agentic deployment.
LLMs Spontaneously Develop Human-Like Brain Regions for Language, Math
LLMs spontaneously develop human-like brain regions for language, math, physics, and social reasoning, per @LiorOnAI. Two optimization processes converged on the same solution.
3 MCP Gateway Security Gaps LiteLLM's Audit Found (And How to Fix Them in
LiteLLM's audit revealed 3 MCP gateway gaps: fail-open resolver, unpinned servers, opt-in least-privilege. Fix them in Claude Code with version pinning and allowed_tools.
FreeLLMAPI Aggregates 1.7B Free Tokens/Month Across 11 Providers
FreeLLMAPI aggregates 11 free LLM providers into one endpoint, offering 1.7B tokens/month with automatic fallover. Reduces friction for side projects but faces provider tolerance risks.
LLMs Default to Zod Schemas, Breaking MCPFusion Security Contracts
LLMs default to raw Zod schemas, bypassing MCPFusion's defineModel() and risking data leaks. The Developer Prover enforces MVA architecture via rejection.
OpenAI, Broadcom Unveil Jalapeño ASIC for LLM Inference
OpenAI and Broadcom unveiled Jalapeño, a custom ASIC for LLM inference, targeting volume deployment by late 2026. No performance metrics were disclosed.
Miami Startup Claims 12M-Token LLM Inference at $8 vs. $2,600 on Claude
Miami startup claims 12M-token LLM inference for $8 vs. $2,600 on Claude Opus 4.6. No paper or benchmarks released yet.
Zalando Introduces MLLM-Based Evaluation for Product Retrieval
Zalando presents a multimodal LLM-based evaluation for product retrieval, aiming to enhance search relevance in e-commerce. This matters as it could set a new standard for assessing AI in retail search.
Never Let the LLM Write the Joins
This article details a two-phase text-to-SQL pipeline: Phase A deterministically plans (intent, entity resolution, joins, RBAC) and Phase B executes with bounded LLM calls. The subject graph caches entity mappings lazily, and security is enforced before the model sees any schema.
Metric Match Cuts LLM Judge Annotation Cost 32.5% via Subset Selection
MIT and Stanford researchers developed Metric Match, a subset selection method that reduces LLM judge annotation costs by 32.5% and estimation error by 18.7%, achieving a 0.838 win-rate against random selection.
Omaha Steaks Shrinks Average Delivery Time to 1.24 Days via Fulfillment
Omaha Steaks cut delivery from 6.2 to 1.24 days via five new fulfillment centers and a UPS Roadie partnership. CEO Nate Rempe says same-day delivery now covers 40-45% of the U.S.
General LLMs Beat Clinical AI Tools in Doctor Study
Frontier LLMs beat clinical AI tools like OpenEvidence in all evaluations, matching Google Search AI Overview.
Clinical LLM Rejection Predictor Hits AUROC 0.719 in 4.5-Month Study
Clinical LLM rejection predictor achieves AUROC 0.719 in 4.5-month study using deployment-specific context to forecast user rejection before response generation.
SVoT Boosts MLLM Spatial Reasoning by 65% via RL-Verified Visual Chains
SVoT uses RL to verify MLLM spatial reasoning states, achieving up to 65% accuracy gains on OOD tests across five domains including Pacman and Gather.
UniSound U2 Cuts Token Use 25%, Joins Top Chinese LLM Tier
UniSound's U2 foundation model cuts token consumption by 25% while matching top Chinese LLM performance, entering the top tier with an efficiency-first design.
PRS 2026: Netflix Workshop Reveals Industry Shift to LLM-Powered
Netflix's 2026 PRS workshop featured DoorDash, LinkedIn, Pinterest, Google DeepMind, and Stanford, showcasing how LLMs are transforming personalization, recommendation, and search. The event underscored the industry's shift toward integrating large language models into core recommendation pipelines.
WorldBench: Top MLLM Scores 64% on Visually Diverse Benchmark
WorldBench, a new multimodal benchmark, tests 15 MLLMs on visually diverse images. Top model scores 64.0%, exposing fundamental gaps in visual understanding.
Chinese LLMs Surge on OpenRouter as U.S. AI Traffic Shifts
Chinese LLMs now drive most weekly token growth on OpenRouter, with American startups routing more traffic to them, per @rohanpaul_ai. The shift reflects utility over brand loyalty.
SMAC-Talk: StarCraft Benchmark Tests LLM Agents Against Deceptive Allies
SMAC-Talk extends StarCraft Multi-Agent Challenge with natural language communication, testing LLM agents against deceptive allies. Qwen3.5 models benchmarked; no model exceeds 72% win rate.
ChatHealthAI: EHR Foundation Model + Frozen LLM Hits 79.8% F1 on Length-of-Stay
ChatHealthAI aligns CLMBR-T-Base with a frozen LLM via a task-aware resampler, achieving 79.8% F1 on EHRSHOT length-of-stay prediction while enabling interpretable reasoning.
New 474-Game Benchmark Reveals LLMs Collapse on Counterfactual Reasoning
New 474-game benchmark reveals LLMs fail on counterfactual reasoning, with larger drops than contextual perturbations. Highlights metacognitive gaps in agentic AI.
Microsoft Markitdown: One-Command File-to-Markdown for LLMs
Microsoft open-sourced Markitdown, a one-command file-to-markdown converter for LLMs, improving output quality by leveraging markdown training data.
Claude.md Hits 152K GitHub Stars; Karpathy Notes LLM Failure Patterns
Claude.md hits 152K GitHub stars. Karpathy notes LLMs fail consistently, driving demand for standardized prompt templates.
ModelBest Drops BitCPM-CANN: First 1.58-bit LLM on Ascend 910B
ModelBest released BitCPM-CANN, the first 1.58-bit ternary LLM on Ascend 910B NPUs, using 6× less VRAM than BF16 with minimal capability loss.
Code-as-Agent Harness Thesis: 88.5% Gains Without Touching the LLM
Paper shows 88.5% improvement by adapting runtime interface around frozen LLM. Harness generalizes across 18 backbones, challenging model-centric agent improvement.
Claude Code Ships /workflows, Replaces LLM Orchestrator with Code
Claude Code /workflows replaces LLM orchestrator with code-based control flow, solving the token tax problem from multi-agent context buildup.
HAVEN Benchmark Exposes MLLM Gap Between Fluency and Video Understanding
HAVEN benchmark tests MLLMs on hierarchical video understanding across frame, shot, and video levels. Results show top models lack grounded multimodal reasoning despite fluent text generation.
Memory as a Model: Augmenting LLMs with Trained Memory
Paper augments LLMs with trained memory for long-term recall. Model-agnostic approach stores external knowledge without retraining.
OpenAI Readies General-Purpose LLM With Test-Time Compute Scaling
OpenAI is releasing a general-purpose LLM that improves with test-time compute, per an internal message. The model shows math gains without specialized training.
Apple Paper Argues LLMs Show 'Illusion of Thinking'
Apple paper argues LLMs show no genuine reasoning, only pattern matching. The critique targets vendor claims but lacks new empirical evidence.