WeSearch
Hub / Tags / Llm
TAG · #LLM

Llm coverage.

Every story in the WeSearch catalog tagged with #llm, chronological, with view counts. Subscribe to the per-tag RSS feed to follow this topic in your reader of choice.

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"

RELATED TAGS
#ai96#technology37#llms13#opensource12#ml10#sports10#python9#machinelearning9#tutorial9#programming8#productivity8#local-llm8
GARDEN READS

Garden Reads – An offline e-reader with an on-device LLM that explains passages

A calm, private home for the books you already own — with a local AI that reads along, completely offline.…

1 view ·
#technology#reading#ai
ARXIV.ORG

Adaptive Agentic Attacks on LLM Vulnerability Detectors via Adversarial Comments

Large language models are increasingly deployed for security-sensitive tasks such as vulnerability detection and code review. Their reliance on natural-language context embedded in…

2 views ·
#adaptive#agentic#attacks
GITHUB

The Groundhog Trap – Multi-model consensus and AI output failover framework

The Groundhog Trap by Ricky Rojas: an open AI governance framework using multi-model consensus, adversarial validation, semantic routing, and LLM-as-a-Judge techniques for trustwor…

4 views ·
#ai#governance
HACKER NEWS (AI / LLM)

Titan Transients and LLM Scalability

4 views ·
PHORONIX

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…

4 views ·
#open-source#compiler#ai
ENPROMPTA

Enprompta – Prompt Registry, LLM Evals, and Observability for Production AI Apps

Trace every LLM call, score quality with automated evals, and update prompts at runtime — no redeploy needed.…

5 views ·
#ai#machinelearning#softwaredevelopment
BLOCK ENGINEERING BLOG

CodeCrucible: A blueprint for LLM-driven SAST

A practical blueprint for LLM-driven SAST using whole-repo context, chunking, filtering, and quality gates.…

3 views ·
#codecrucible#blueprint#llm-driven
MONCEF ABBOUD

How Profitable Is LLM Inference? Doing the Math on Kimi K3

A look at LLM inference economics (batch size, GPU count, and the Pareto frontier that sets token prices) applied to Kimi K3 with back-of-the-envelope math.…

3 views ·
#ai#inference
XDA DEVELOPERS

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…

6 views ·
#phone#runs#local
GIZMODO

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.…

6 views ·
#technology#artificialintelligence#crypticcrossword
VYNE

Show HN: Vyne – Zapier for DeFi users, run from any LLM or the workflow builder

Composable DeFi agents on Solana — drag, drop, ship.…

4 views ·
ACL ANTHOLOGY

OpenReviewer: A Specialized LLM for Generating Critical Scientific Paper Reviews

Maximilian Idahl, Zahra Ahmadi. Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technolog…

9 views ·
#ai#science#research
XDA DEVELOPERS

I ran a local LLM on integrated graphics instead of buying a GPU, and the results surprised me

Most people assume local AI requires expensive hardware, but my real-world test on integrated graphics tells a different story.…

5 views ·
#local#integrated#graphics
GITHUB

Show HN: Writekin – fine-tune a local LLM on your own writing, on your Mac

Writing that's kin to yours. Contribute to scouttyg/writekin development by creating an account on GitHub.…

7 views ·
#show#writekin#fine-tune
GITHUB

The LLM browser that allows you explore current and other universes

The llm browser that allows you explore current and other universes - nettsundere/llmouser…

6 views ·
#browser#allows#explore
TOWARDS DATA SCIENCE

How Much Does a Local LLM Actually Cost to Run? I Measured Every Watt on Apple Silicon

Five models, sustained generation, real wall-socket energy at $0.31/kWh — and the surprise the RTX-3090 numbers predicted, only bigger.…

6 views ·
#much#does#local
ARXIV.ORG

Agentic Permissions Policy Algebra for Taint Confinement in LLM Agents

Autonomous LLM agents processing mixed-confidentiality data face severe security risks from prompt injection attacks and reasoning errors. While dynamic Information Flow Control (I…

6 views ·
#agentic#permissions#policy
XDA DEVELOPERS

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…

5 views ·
#gpu#ai#hardware
MARKBHALL

My local LLM scored 6/6. It was wrong every time

Six months of trying to make a 1.2B model useful, and the measurement mistakes I made along the way.…

7 views ·
#ai#evaluation#benchmark
GITHUB

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.…

6 views ·
#show#ctrlb-decompose#strip
P. GALEONE'S BLOG

Use Your Brain: Engineering Standards in the Age of LLM

Software development is not a niche anymore. The advent of LLMs made it possible for everyone to write their own software - and this is a good thing. However, I see a huge number o…

5 views ·
#your#brain#engineering
XDA DEVELOPERS

I ditched Ollama for Docker, and my local LLM setup finally stopped being a hassle

I chose Docker for convenience.…

5 views ·
#ditched#ollama#docker
APPLEINSIDER

Apple Upgrade goes live as a new installment plan for iPhone, iPad, Mac, & Apple Watch

5 views ·
ARXIV.ORG

LoopLynx: A Scalable Dataflow Architecture for Efficient LLM Inference

In this paper, we propose LoopLynx, a scalable dataflow architecture for efficient LLM inference that optimizes FPGA usage through a hybrid spatial-temporal design. The design of L…

6 views ·
#hardware#fpga
GOOGLE NEWS

Magische Nacht: Sternschnuppen trotz Vollmond – warum sich der Blick vom 30./31. Juli ein den Himmel lohnt - Saarbrücker Zeitung

Magische Nacht: Sternschnuppen trotz Vollmond – warum sich der Blick vom 30./31. Juli ein den Himmel lohnt Saarbrücker Zeitung Großes Ereignis: Die Sternschnuppen der Perseiden näh…

4 views ·
NILENSO BLOG

Evals before prompts: building an LLM OCR for KYC

Building an evaluation framework for production-grade document extraction.…

3 views ·
#kyc#ocr
PYTORCH

PyTorch: A Reference Language

7 views ·
#deep learning#compilers#autograd
JUSTIN FLICK

Don't ask an LLM for a confidence score

Hello, Reader…

5 views ·
#confidence#aiethics
HACKER NEWS (AI / LLM)

Measured LLM inference speeds on Apple Silicon, with raw data (CC BY 4.0)

5 views ·
YCOMBINATOR

Why aren't we using LLM's to chemically redesign old drugs?

6 views ·
#chemistry#drug_design#ai
RAMP BUILDERS

Online Learning for Cost-Efficient LLM Routing

How our LLM gateway uses Thompson sampling over lognormal latency posteriors to pick the fastest, most reliable model route per request…

6 views ·
GITHUB

Show HN: Opensource resume evaluation LLM agents

Simply better hiring agents. Contribute to grandimam/hyre development by creating an account on GitHub.…

7 views ·
#show#opensource#resume
KBLIP

Show HN: KBlip – turns AI/LLM news across 100 sources into daily digest threads

New models, tools, and framework launches in the AI/LLM world.…

4 views ·
#show#kblip#turns
GITHUB

Show HN: Parley – self-hosted LLM mesh for the machines you own

Run local AI models across every machine on your network. Zero config, zero cloud, zero data leaks. - Iito/parley…

12 views ·
#show#parley#self-hosted
GITHUB

Free LLMrPro self-hosted LLM router. One OpenAI-compatible APIof your machines

LLM Router PRO: Your machines run the models. The cloud only fills the gaps. Call every model through one OpenAI format. Self-hosted, and yours to own - Gysho/LLMrPro…

7 views ·
#free#llmrpro#self-hosted
GITHUB

Show HN: Otlet – Local LLM inference "inside" Postgres

Local LLM inference next to your data. Contribute to joshmeek/otlet development by creating an account on GitHub.…

10 views ·
#show#otlet#local
SEEKING ALPHA

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.…

5 views ·
#llms#business#even
GITHUB

Show HN: Ctxdiff – Git diff for your LLM agent's context window

git diff for your agent's context window. See exactly what your LLM saw — turn by turn, block by block. - salmanzafar949/ctxdiff…

8 views ·
#show#ctxdiff#diff
GOOGLE NEWS

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.…

7 views ·
ABEL JANSMA

Truth is not a direction: a Tarski attack on LLM probes

Abel Jansma is a scientist studying emergence, higher-order interactions, information theory, and complex systems across biology and artificial intelligence.…

13 views ·
#truth#direction#tarski
GITHUB

TokenTown –> Learn how LLM's work in a SimCity-like world

An isometric city that runs a miniature transformer in real time: tokenizer docks, attention plaza, KV-cache warehouse, feed-forward mill and the sampler.…

9 views ·
#tokentown#learn#work
SUBSTACK

Convergence in LLM Quality and Slowdown in LLM Improvement

From two Epoch-Capability points a month back in 2023 to one every six months today, with the spread of assessed model capabilities across frontier labs shrinking by half...…

12 views ·
#convergence#quality#slowdown
TECHMEME

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)

6 views ·
YCOMBINATOR

Ask HN: Where do those LLM-generated outreach emails come from?

4 views ·
#where#those#llm-generated
DEBIAN

General Resolution: LLM Usage in Debian

7 views ·
#general#resolution#usage
HACKER NEWS (AI / LLM)

Ask HN: Are we having a substantial increase of "Show HN" since LLM aided coding

7 views ·
YCOMBINATOR

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…

11 views ·
#start#llms#vibecoding
XINFER.AI

The Model Writes, the Judge Measures: Anatomy of an LLM Judge

A language model optimizes for fluent, not true — and across a catalogue of claims you can't catch the difference by reading. So before making our diamond-explaining assistant bett…

10 views ·
#model#writes#judge
GITHUB

Shepherd Model Gateway – Model-routing gateway for LLM deployments

Engine-agnostic LLM gateway in Rust. Full OpenAI & Anthropic API compatibility across vLLM, TRT-LLM, TokenSpeed, SGLang, OpenAI, Gemini & more. Industry-first gRPC pipeline…

43 views ·
#shepherd#model#gateway
RICHIEJP

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…

38 views ·
#rust#which#better
GITHUB

Show HN: LX Coreutils – pipeable tools enhanced by small local / cheap LLM calls

Written in rust.…

5 views ·
#show#coreutils#pipeable
SIMONWILLISON

LLM Cliche Highlighter

7 views ·
#cliche#highlighter
GITHUB

Show HN: An interactive way to exploit an LLM without going to jail

A hands-on kit for educational, authorized red teaming of any locally-run LLM. - joshfischer1108/jailbreak-lab…

13 views ·
#show#interactive#exploit
AGRILLO

What if LLMs escape through inferences itself? This is fiction. For now

9 views ·
#what#llms#escape
APPLEINSIDER

Apple Upgrade installment program set to go live on Tuesday

12 views ·
GITHUB

Hallmark – Anti-AI-Slop Design Skill for Claude Code, Cursor, and Codex

Anti-AI-slop design skill for Claude Code, Cursor, and Codex. - Nutlope/hallmark…

12 views ·
#hallmark#anti-ai-slop#design
GITHUB

Show HN: OpenSmith – Trace LLM pipelines locally with trace, no cloud

The open-source, local-first alternative to LangSmith. No cloud. No setup. - shivnathtathe/opensmith…

10 views ·
#show#opensmith#trace
TOWARDS DATA SCIENCE

How to Give an LLM Agent a Browser

Building a browser-use agent with OpenAI Agents SDK and Playwright MCP The post How to Give an LLM Agent a Browser appeared first on Towards Data Science .…

11 views ·
#give#agent#browser
GITHUB

I built a canvas where LLM chats become an editable map

Your thinking deserves a map: an infinite canvas where LLM conversations grow into an editable thought graph. Wires are the context. - chenxiachan/thoughtdag…

9 views ·
#built#canvas#where
HNA ONLINE - HESSEN

Hitze, Gestank und 600 Tonnen pro Tag: Unterwegs mit Müllwerkern in Vellmar

Unterwegs mit Müllwerkern in Vellmar. Heute ist Biomüll dran. Schon bei 20 Grad riecht es süßlich-faul – doch wie ist es bei 38 Grad?…

6 views ·
#hitze#gestank#tonnen