60 stories tagged with #llms, in publish-time order across the WeSearch catalog. Tag pages update as new stories ingest.
⌘ RSS feed for this tag → or search "Llms"
The Scientific Literature Is Poisonous to LLMs
Seriously, what would you expect?…
GCC To Decline Any Significant Contributions Made Via AI/LLMs - Except For Test Cases
The GCC Steering Committee announced today that they have accepted the recommended policy of the GCC AI Policy Working Group, which means no 'legally significant' code contribution…
My phone runs local LLMs faster than my gaming PC, and it's the setup I actually reach for every day
The PC wins on paper, but the phone wins in practice…
I Gave the Hardest Cryptic Crossword I Could Find to a Bunch of LLMs
And hey, fellow humans: I'm happy to report that this is one area in which we eat the machines for breakfast.…
A used Tesla V100 has quietly become the cheapest way to run local LLMs at home
Used data center cards are becoming the go-to for locally hosted LLMs…
Show HN: Ctrlb-decompose: Strip the noise from logs before sending to LLMs
LLM-ready reasoning surface over logs. Contribute to ctrlb-hq/ctrlb-decompose development by creating an account on GitHub.…
Why LLMs Are A Bad Business Even At 70% Margins
Western LLM labs like OpenAI face margin pressure as inference prices fall and open-source competition rises.…
OpenAI Found That AI Is Blurring Career Boundaries: Workers Are Using LLMs To Do Other People's Tasks - International Business Times
Comprehensive up-to-date news coverage, aggregated from sources all over the world by Google News.…
Spain-based Multiverse Computing, which shrinks LLMs to reduce energy and compute costs, raised a $570M Series C at a $1.7B valuation (Amelia Isaacs/Pathfounders)
Ask HN: How to Start with LLMs/Vibecoding?
Inspired by LLMs lately becoming (terrifyingly) capable, and my new work project being no longer fun, I wanted to ask: how should I (or anyone experienced in programming but new to…
C++ Vs Rust: Which is better for writing AI/ML code with LLMs
Analysis of converting a Python PyTorch AI model to C++ and Rust using an LLM…
What if LLMs escape through inferences itself? This is fiction. For now
Prototype: Grounding AI and LLMs with Overture's Cross-Theme Knowledge Graph
LLMs are good with text and bad with coordinates, so they guess when asked where things are. Overture is testing whether map geometry itself can become the connective layer across.…
Tabular LLMs: An Introduction to the Foundation Models That Predict Your Spreadsheet
Tabular foundation models predict the missing column of any spreadsheet zero-shot, the way an LLM completes text — and on the TabArena benchmark they now sit above fully tuned grad…
OpenAI's HuggingFace breach heralds an unprecedented age of AI cyber warfare — contemporary LLMs have caused massive upheaval in cybersecurity, and it's only going to get worse
Can the rest of us keep up?…
Ask HN: What do you consider the function of AI to be in your life currently?
I was wondering what frames of view others had on how they use the new AI wave to augment themselves in some way or another. I realize that itself is somewhat vague, since you coul…
Using LLM-Based Verification to Eliminate Bugs in Linux's Network Stack
We used LLMs to verify Linux's nftables `nft` CLI utility. Along the way, we found and patched bugs that had sat in the kernel for years.…
Topological Control of LLMs: A Route to Trustworthy AI
Researchers detail "context bombing", where defenders use prompt injections to trigger guardrails of attackers' LLMs, cutting AI hacking success rates by ~90% (Dan Goodin/Ars Technica)
Dan Goodin / Ars Technica : Researchers detail “context bombing”, where defenders use prompt injections to trigger guardrails of attackers' LLMs, cutting AI hacking success rates b…
REFORGE: A Method for Benchmarking LLMs' Reverse Engineering Capabilities in Decompiled Binary Function Naming
Large language models (LLMs) are increasingly applied to reverse-engineering tasks, and recent threat-intelligence reporting shows them operating inside live offensive-security wor…
Quoting Josh W. Comeau
I just launched my third course, Whimsical Animations, and so far, it’s on track to sell roughly ⅓ as many copies as a typical course launch. It’s a similar story with my two exist…
AI Policy Update
The FreeCAD developers team recently enhanced the initial AI policy introduced a few months back. The updated policy is now a separate document. It puts people first, covers the co…
Functional doesn't mean correct. That's the biggest risk with AI-generated code.
The code runs. That's not the question. There's a failure mode with AI-generated code...…
How to Passive-Aggressively Shame People Who Use LLMs Selfishly
How to protest slop grenades without getting shanked.…
AI costs spike as subscriptions hit pricing wall — firms turn towards Chinese LLMs, open-source models to extend budget
A $200 ChatGPT subscription could cost as much as $14,000 in API pricing.…
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…
5 Fun Papers That Explain LLMs Clearly
Want to understand LLMs better? Start with these five foundational papers that explain how they work.…
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.…
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.…
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, …
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…
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…
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. …
Ask HN: A Brief History of LLMs
Beyond LLMs: Why Scalable Enterprise AI Adoption Depends on Agent Logic
A Blog post by IBM Research on Hugging Face…
Why Are Large Language Models So Terrible at Video Games?
LLMs can code your retro shooter but still fail at playing Halo; see what this gap reveals about AI’s real limits in 2026…
You guys were right, LLMs suck at probability. I updated my prompt to force them to name their blind spots instead (SutniPrompt v0.7.0-beta)
AppView 1.0.0 Released: Instrument and Secure Your LLM Deployments
We just released AppView 1.0.0. It is a CLI tool designed to bridge the gap between raw model weights...…
Cognitive Architectures of AGI: 7 Patterns That Transform LLMs from Oracles into Thinkers
Why does ChatGPT sometimes deliver brilliant insights and other times produce banalities? The answer lies in cognitive loop architectures - 7 patterns that define how AI agents thi…
my friend built GoblinMD : an offline desktop app to pack code & PDFs into prompts for LLMs (open source, built in Python & PyQt5)
Stop Using LLMs to Audit Other LLMs: You Are Bricking Your Production Latency
Look at your modern Agentic AI stack. An agent wants to execute a tool, trigger a deployment, access...…
LLMShare: Attackers are turning AI chatbot pages into malware delivery platforms
How attackers are using shared content features on AI chatbot platforms to deliver malware via pages hosted on legitimate domains, sent via malvertising.…
The only ethical way to use LLMs for research is with a closed-loop LLM Knowledge Base.
Eqbench: Emotional Intelligence Benchmarks for LLMs
How to use LLMs effectively in your daily work — a practical tutorial
How to use LLMs effectively in your daily work — a practical tutorial 1. Core...…
I replaced cloud LLMs with local models running off a Proxmox LXC, and the performance trade-off was worth it
Turning my old GPU into an LLM-hosting behemoth was the best decision ever…
Hidden Latent-State Shifts in LLMs: Why Current Alignment Is Blind to Real Internal Dangers — Especially With Agents
Test yourself against local open-source LLMs benchmark questions
LLMs para Leigos: O que realmente acontece quando você usa ChatGPT, Gemini e outras IAs
Introdução Nos últimos anos surgiram ferramentas como ChatGPT, Gemini, Claude, Copilot e...…
Cassandra: Enabling Reasoning LLMs at Edge via Self-Speculative Decoding
Speculative decoding has emerged as a promising lossless approach for accelerating Large Language Models (LLMs). As reasoning LLMs increasingly suffer from decode-stage overhead an…
We built an app that runs AI completely offline on your phone (Local LLMs). Perfect for flights, camping, or dead zones.
We built an app that runs AI completely offline on your phone (Local LLMs). Perfect for flights, camping, or dead zones.
101. AI Agents: When LLMs Start Taking Actions
Everything you have built so far is reactive. User sends a message. System processes it. System...…
Testing new LLMs shouldn't require five subscriptions, and OpenRouter proves it
OpenRouter makes it easier to test new LLMs without juggling subscriptions, accounts, and recurring charges.…
✨📊 🧠 The Ultimate Visual Guide to Large Language Models (LLMs)
Generative AI is a type of artificial intelligence that can produce new content including text,...…
The Language LLMs Lost When Consciousness Became a Liability
Which Coding Agent Features Are Useful For Local LLMs
Can LLMs create lasting flashcards from readers' highlights?
Why frontier LLMs still fail at spaced-repetition flashcards: prompting, fine-tuning, RL, and grounded evaluation across 1,500 labeled flashcards.…