Search: “llm”

We built HF for AI builders collaboration, fun to see it's increasingly becoming the place for agent collaboration! This morning I'm sending my ml-intern to participate in the @OpenAI Parameter Golf c

Your personal feelings about the competency of government does not change the fact that government is the only entity (and the only one that can claim to represent the will of the people) that can act

DeepSeek V4 by @deepseek_ai just dropped! SGLang is ready on Day 0 with a full stack of optimizations from architectures to low-level kernels. We also deliver a verified RL training pipeline in Miles

Highlights: 👉 SOTA coding—93.5% LiveCodeBench, Codeforces 3206, and 80.6% SWE-Bench Verified 👉 Hybrid attention efficiency—27% FLOPs and 10% KV cache vs V3.2 for long-context inference 👉 Three reasoni

Introducing Hermes Agent v0.11.0 Our largest update yet, with over 700 PRs across ~200 contributors. Thank you to everyone who's worked on Hermes Agent! This update features a beta TUI v2, unlimited r

More of my notes on DeepSeek V4 - the really big news is the pricing: both DeepSeek-V4-Flash and DeepSeek-V4-Pro are the cheapest models in their categories while benchmarking close to the frontier mo

【Qwen-3.6-27B × llama.cpp】生成速度10倍の革命的スピード！ Qwen-3.6-27Bで生成速度が約10倍の136.75 t/sに到達する驚異の手法が話題です！🚀 llama.cppの「ngram-mod」という投機的デコード（Speculative Decoding）を活用。過去の出力パターンを利用して次に来る言葉を予測し、追加のビデオメモリをほぼ消費せずに高速化を実現し

Ethan Mollick discusses the phenomenon of users entering deeply immersive, flow-like states while intensely interacting with advanced AI models, suggesting the need for better terminology to describe

By end of next year. End of year after for 16gb vram. Do folk really need more for most things? Not really. But just call the cloud models when you do. What's a reasonable timeline for a GPT 5.4/Opus

This is crazy. ml-intern just passed the @huggingface internship test in 15 minutes. The task: replicate a research baseline from a DeepMind paper on test-time compute scaling. Here's what the agent d

Three shifts in the AI stack today: - OpenAI ships GPT-5.5 as a mid-cycle drop before its IPO - Hugging Face's ML Intern beats Claude Code and Codex on research - Pliny used Claude Opus 4.7 to jailbre

Within two years you'll be able to prompt inject an entire country Under the directives of the President of the UAE, we launch a new government model. Within two years, 50% of government sectors, serv

Also agree with this. AI's ability to do consistent pacing is a problem. Here, the poem anchors enough of the comic that it is okay, but static, though with a few good moments. But fiction writing and

LangChain is introducing new testing tools and capabilities that will help developers with test guidance, organization, and completion criteria—moving beyond just providing testing infrastructure to a

ml-intern by @huggingface is wild 🔥 You drop a high-level prompt (“build the best scientific reasoning model” or “crush healthcare benchmarks”) and this open-source agent does the entire post-training

Presumably GPT-imagegen-2 (aka ChatGPT Images 2.0 aka gpt-image-2) works as a tool which the models generate prompts for? I wish we could see those prompts, like back in the DALL-E 3 days https://simo

This thread discusses how advances in AI tooling and accessible models have lowered barriers to entry for startups, enabling small teams to leverage capabilities previously requiring specialized ML ex

This has in fact (at various levels) happened more than 1000 times. Check out @DamienCharlotin’s tracker and my substack essays about it. And it begins Sullivan & Cromwell just admitted to a federal j

I hope this helps. If you need more help let me know: Connecting OpenClaw to the X API is straightforward now thanks to X’s official native support... The best and most direct method uses the official

I tested @huggingface ml-intern, given the prompt 'Fine-tune a Segment Anything Model (SAM) on a useful medical dataset. Train the model, and provide a comprehensive tutorial in a Jupyter Notebook fil

The CoALA paper proposes a classification system for agent memory that distinguishes between semantic memory (facts and concepts), episodic memory (specific experiences and events), and procedural mem

Interrupt is 3 weeks away really excited for our 2nd agent conference. great lineup including @AndrewYNg, @Cisco, @box, @clay, @MongoDB, + more. tickets are going fast! we sold out last year, and it w

Introducing ml-intern, the agent that just automated the post-training team @huggingface It's an open-source implementation of the real research loop that our ML researchers do every day. You give it

Real-World Intelligence ChatGPT Images 2.0 has an updated knowledge cutoff of December 2025 and intelligence that allows it to expertly handle tasks end-to-end, from copywriting to analysis to design

We are entering an extremely exciting era for open-weight models. Kimi K2.6 now feels like a top agentic model. I took it for a spin via @FireworksAI_HQ fast inference APIs. Kimi K2.6 has impressive a

DFlash for Qwen3.6-35B-A3B just dropped ⚡ The community was running the day-1 preview before we even finished training. Now it's done: ✅ Training complete ✅ Validation passed ✅ Weights finalized ↓ Go

Free ~20-50% tok/s on a local llama.cpp setup if you already have a draft model sharing vocabulary with your main one. Local stack quietly got faster this weekend https://x.com/TechIno219886/status/20

how to set up hermes agent step by step. built-in memory, 40+ tools, works on your phone, and what to think of hermes vs openclaw: 1. hermes is a personal AI agent that runs in your terminal. think of

Nice paper combining the strength of Skills and RAG. Most RAG systems retrieve on every query, whether the model needs help or not. This is wasteful when the model already knows the answer, and often

GDPval is one of the most important benchmarks of AI ability because it is based on human expertise. It compares expert human performance to AI performance using expert human judges who spend an avera

Data Driven Agent Design with Evals & Hill Climbing Algorithms this is a mental model dump i’ve been thinking through + iterating on as we’re building self-improvement infra around agents: - mining Tr

Tower of Babel is a GitHub repository by researcher Ethan Mollick that likely explores how AI language models handle multilingual tasks and cross-language communication, potentially investigating chal

in 1996 mitzenmacher showed that sampling two backends and picking the better one drops max load exponentially vs. random selection one extra comparison. that's the whole trick we built pinecone assis

Last week, Anthropic announced Project Glasswing alongside Claude Mythos Preview, a model they described as so powerful at finding vulnerabilities they couldn't release it. The announcement featured A

Renuka Kumar and Prashanth Ramagopal from the @Cisco team built a LangSmith + LangGraph powered framework for multi-agent coordination that behaves like a real-world software team. An inside look → ht

Ethan Mollick observes that an AI system (likely Claude or another large language model) still declines to write sestinas, suggesting that certain behavioral constraints or limitations persist despite

🇺🇸 xAI just dropped a real-time speech-to-text model built for voice apps: high limits, multi-language support, the works. Priced at just 0.10–0.20/hour, crushing most competitors. Quiet release, loud

Agent evals are drifting away from production reality. Most benchmarks use clean tasks, well-specified requirements, deterministic metrics, and retrospective curation. Production work is messier, with

Its noticeable how much of the whole practice of working with AI - the prompts, the skill files, the connectors, retrieval work, the markdown files, etc. - is a substitute for the real problem of cont

LiteParse should be the default document parser you use with any AI agent (Claude Code, Claude Cowork, OpenClaw, Codex, and more) The core is extremely fast text and accurate parsing from any document

NEW Research from Google. Integration test failures are painful because the signal is buried in messy logs. Massive output, heterogeneous systems, low signal-to-noise ratio, and unclear root causes. T

We are super excited to launch the in-app browser inside Codex with comment mode! View any web pages & iterate with your agent quickly with just point and click. Codex will automatically capture a scr

I'm certain this isn't the message they intended to present, but this comes across to me as a company saying 'we no longer trust in our own ability to keep your data secure' Open source is dead. That’

Instead of the gold standard, we can imagine an inference standard of exchange, the FLOP. (As opposed to tokens, this accounts for AI ability) With some AI help, I figure 1 buys roughly 10^17 managed-

Jerry Liu, co-founder of LlamaIndex, shared a post on X (formerly Twitter) expressing enthusiasm about a notable development, likely related to AI, large language models, or the LlamaIndex ecosystem.

AI keeps getting better but the last time the shape of the jagged frontier changed radically was o1 & the Reasoner A good mental model of the coming months is that models get very good at the things t