60 stories tagged with #llm, in publish-time order across the WeSearch catalog. Tag pages update as new stories ingest.
⌘ RSS feed for this tag → or search "Llm"
Show HN: Meadow Mind – a 7B diffusion LLM plays Gym games with zero training
Zero training, second-level reactions (~400ms). A language-rule decision mind on a local 7B diffusion LM. - Hey-Meadow/meadow-mind…
Anthropic secretly limiting Claude's usefulness for LLM development strengthens the argument that Anthropic is using AI safety to justify monopolistic behavior (Dean W. Ball/@deanwball)
Dean W. Ball / @deanwball : Anthropic secretly limiting Claude's usefulness for LLM development strengthens the argument that Anthropic is using AI safety to justify monopolistic b…
At Texas A&M, Falling Enrollment Isn’t a Concept
Big state universities are defying the notion of a higher education bubble, even as smaller colleges struggle to stay open.…
There’s really only one solution for USMNT heading into World Cup with uncertainty
The most interesting tactical wrinkle introduced by Mauricio Pochettino on Saturday was also a nod to how his U.S. men’s national team needs to play.…
Running Python code in a sandbox with MicroPython and WASM
I've been experimenting with different approaches to running code in a sandbox for several years now, but my latest attempt feels like it might finally have all of the characterist…
ToTra – open-source LLM gateway with GDPR/EU AI Act compliance
Open-source AI gateway for enterprises — quota, PII protection, cost tracking, and compliance - SugaC-275/ToTra…
Clippers star Kawhi Leonard, owner Steve Ballmer interviewed for role in Aspiration scandal
NBA investigator interviews have begun for Los Angeles Clippers superstar Kawhi Leonard and his uncle and business adviser, Dennis Robertson, per ESPN. Leonard, Robertson, and Clip…
Fine-tuning an LLM to write docs like it's 1995
In my predictions for 2030 I wrote that tech writers would be using specialized LLMs, running locally on powerful hardware. I see hints of this move to “local first” among engineer…
7 benefits employees can use outside of open enrollment
If an employer wants to retain employees, they should consider perks that have an impact throughout the year.…
USMNT’s New York stars embracing Knicks fever during World Cup build up
The USMNT's New York natives have embraced the Knicks' run like so many other lapsed fans who’ve rediscovered their dedication amid the playoff run.…
I built a vulnerable app and spent $1,500 seeing if LLMs could hack it
As a part of my work I do security research for various apps and websites. I wanted to see if LLMs could reproduce a common class of exploits I've found in multiple apps. So I buil…
TensorSharp: Open-Source Local LLM Inference Engine
A C# inference engine for running large language models (LLMs) locally using GGUF model files. TensorSharp provides a console application, a web-based chatbot interface, and Ollama…
Hands Free: What LLM Driven Vulnerability Research Looks Like
Agentes de IA: cómo un LLM razona, usa herramientas y actúa solo
Un agente de IA es un LLM metido en un bucle que razona, elige herramientas y ejecuta acciones hasta cumplir una meta. Te explicamos cada pieza con có…
This day in LLM history….105 years ago today, Qwen 3.6 27b was released open source. /s
Show HN: On-device Chrome extension that blocks credential leaks to LLM chats
Catch credentials and PII before pasting into ChatGPT, Claude, Gemini, and more LLM chats. Runs entirely on your device. Free, open source.…
How Taalas Prints an LLM onto a Chip With $169M in Funding
Discover how Taalas prints LLM onto a chip, revolutionizing AI deployment with faster, efficient on-device intelligence. Learn the process now.…
US Treasury Secretary Bessent meets with LLM labs in San Francisco
US Treasury Secretary Scott Bessent met with LLM leaders in San Francisco, underscoring the need for regulation amid AI's growing cyber role.…
I developed a hard LLM Challenge
My Latest LLM Workflow and Modern Engineering Values
Modern engineering values.…
Obamacare Enrollment Fraud May Cost Taxpayers Billions In 2026, New Study Shows
'A perfect storm'…
LLM as Router: Intent Classification for a Local Telegram Email Agent
In the first article, I showed the whole Llamail system: Gmail, Telegram, n8n, FastAPI, llama.cpp,...…
Trader – LLM agent for Robinhood with a Rust safety layer and paper trading
Contribute to zhangxd6/Trader development by creating an account on GitHub.…
Show HN: Aura, an LLM coding harness that dogfooded itself
An AI coding harness that dogfooded itself into shape: Planner/Worker agents, repo awareness, surgical edits, validation, recovery, and safe diff approvals. - CarpseDeam/Aura-IDE…
Interesting- What LLM vuln research looks like
5 Fun Papers That Explain LLMs Clearly
Want to understand LLMs better? Start with these five foundational papers that explain how they work.…
Parents seek spots with popular schools despite record-high allocation results
About 86 per cent of children secured one of their top three primary school choices through central allocation, up from 79 per cent.…
Which LLM Memory for AI Agents?
1. Executive Summary 2. Project Breakdowns 1. mem0ai/mem0 (⭐57.3k) 1. MemPalace/mempalace (⭐53.2k) 1. Lum1104/Understand-Anything (⭐47.8k) 1. pi…
Mapping AI-enabled cyber threats: Insights from the LLM ATT&CK Navigator
MannKind completes patient enrollment in nintedanib DPI trials
When scraping orchestration is the wrong abstraction for LLM workflows
LLM apps often need structured web data, not a scraping platform. Here's how to choose between orchestration and a simple extraction API.…
Mapping AI-enabled cyber threats: Insights from the LLM ATT&CK Navigator - Anthropic Red
Comprehensive up-to-date news coverage, aggregated from sources all over the world by Google News.…
Microsoft forms partnership with Unsloth AI about local LLM execution
Local models are coming to your laptop soon! 🚀 We're excited to partner with @Microsoft to enable millions of developers run local models on Windows!…
Bedrock plus an external llm router for a year, the audit trail gap we ran into
Show HN: GymCoach – Self-hosted workout tracker where you bring your own LLM
Self-hosted AI workout tracker. Bring your own LLM (Anthropic or OpenRouter): weekly debriefs, a chat coach, and AI-generated programs. - Julien-Au/gymcoach…
Why Your LLM Agent Gives a Different P-Value Every Time (And What to Build Instead)
How LLM-driven statistical analysis silently produces non-reproducible results, and a design pattern (claims ledger + deterministic plugins) that fixes it.…
llama.cpp b9455 Finally Caught vLLM: 70t/s on 2x3090 Qwen 27B UQ8
Test post…
Running 35B–400B LLMs on a GPU-less Cluster to Mine 10,000 Papers — and the 4 Bugs That Almost Ruined the Data
A field report: a CPU-only, GPU-less distributed LLM pipeline (llama.cpp + quantized MoE) mining 10,000 papers — and the 4 silent data-quality bugs that nearly ruined the results.…
CLAUDE.md Compaction: Why Your Rules Disappear Mid-Session
You spent an hour writing a tight CLAUDE.md. Clear rules. Good structure. Specific constraints for...…
"what if you don't have the dataset?"
Discovering the LLM's curious and remarkable world knowledge of open data on the web.…
Benchmarking LLM-as-a-Judge for Long-Form Output Evaluation
As large language models (LLMs) are increasingly used for long-form generation, reliably evaluating long-form outputs has become a critical challenge. LLM-as-a-judge offers a scala…
Does Llms.txt Replace Sitemap.xml
sitemap.xml tells crawlers what exists. llms.txt tells AI agents what matters. If you run docs in 2026, you probably want both.…
TriEval: A Resource-Efficient Pipeline for LLM Bias, Toxicity, and Truthfulness Assessment
LLMs have evolved from basic chatbots to the backbone of the AI ecosystem, now widely used in healthcare, schools, and government services. The domain-wide adoption of LLMs necessi…
SkillDAG: Self-Evolving Typed Skill Graphs for LLM Skill Selection at Scale
As LLM agents adopt large skill libraries, selecting the right subset becomes a structural problem rather than a similarity-matching one: skills depend on, conflict with, specializ…
DELTAMEM: Incremental Experience Memory for LLM Agents via Residual Trees
Large Language Model (LLM)-based agents increasingly rely on memory to learn from experiences over continual interactions. However, storing experiences as independent, flat units l…
The Shadow Price of Reasoning: Economic Perspective on Optimal Budget Allocation for LLMs
Inference-time scaling has emerged as a critical avenue for enhancing Large Language Models' performance, yet real-world deployment is constrained by strict computational budgets. …
EvoTrainer: Co-Evolving LLM Policies and Training Harnesses for Autonomous Agentic Reinforcement Learning
Autonomous LLM training is often framed as recipe search, which leaves the training harness largely static. This limitation sharpens in agentic RL, where shifting bottlenecks and s…
Uncertainty-Aware Clarification in LLM Agents with Information Gain
Large Language Model (LLM) agents often operate under underspecified user instructions, where latent uncertainty over user intent leads to erroneous tool actions. To address this c…
GTBench: A Curriculum-Grounded Benchmark for Evaluating LLMs as Mathematical Research Assistants in Graph Theory
Large language models (LLMs) are increasingly used as self-study assistants in technical disciplines, yet their reliability as mathematical reasoning assistants remains poorly unde…
Distilling Answer-Set Programming Rules from LLMs for Neurosymbolic Visual Question Answering
Visual Question Answering (VQA) is the task of answering questions about images, requiring the integration of multimodal input and reasoning. Modular approaches that incorporate lo…
LEAP: Supercharging LLMs for Formal Mathematics with Agentic Frameworks
Large Language Models (LLMs) exhibit strong informal mathematical reasoning but struggle to generate mechanically verifiable proofs in formal languages like Lean. We present LEAP, …
Cross-Lingual Token Arbitrage: Optimizing Code Agent Context Windows via Local LLM Preprocessing
AI-assisted coding agents are bottlenecked by input-token cost. Two pathologies of raw human input drive much of this overhead: tokenization inefficiency for non-English text and s…
Gender-Dependent Diagnostic Substitution in LLM Medical Triage: Same Symptoms, Unequal Urgency
We investigate whether large language models produce different medical triage recommendations for identical neurological symptoms when only the patient's stated gender and age vary…
Diagnosing Knowledge Gaps in LLM Tool Use: An Agentic Benchmark for Novel API Acquisition
Large language models for code generation often need to use APIs that are absent from their pretraining data. This requires more than recalling a function name: models must coordin…
EvoDrive: Pareto Evolution for Safety-Critical Autonomous Driving via Self-Improving LLM Agents
Generating safety-critical scenarios is essential for validating and improving autonomous driving systems, yet it inherently requires maximizing adversariality to expose failures w…
Dynamic Objective Selection with Safeguards and LLM Oversight for Financial Decision-Making
Financial decision-making tasks such as stock recommendation and portfolio allocation typically estimate future return and risk and then select trades or allocations for an investo…
Migrating macOS fleet from Mosyle to FleetDM with NO Apple Business Manager — manual/user-approved enrollment strategy?
Fitting WhisperX large-v3 + a 24B LLM on one 3090: a reproducible context-capping recipe
This is the technical, reproducible version of a fix I shipped on my own homelab. If you want the...…