Search: “agents”

There are more document parsing models than ever, and they’re getting harder to tell apart. That’s why we built OpenDocRouter. Every model we serve is benchmarked on ParseBench, with latency and cost

Mistral AI demonstrated a tooling solution for engineering drawings that employs the **Mistral Large** model across **four zoom levels**, automatically inspecting and verifying plan details until an e

this is what i'm talking about! https://x.com/sciencegirl/status/2109693723953000631?s=20 Researchers have taught a robotic hand to move independently. By treating its fingers as legs, AI learns to co

The team has announced the launch of **LlamaIndex**, an open‑source information‑retrieval library, with its main site listed at **llamaindex.ai**. The announcement was shared on Twitter by Imaan Sulta

OpenAI introduced interactive in‑chat tools that let users play games or run utility calculators—such as an interactive budget planner—directly within a conversation. The demonstration, released on Oc

Imaan Sultan delivered a well-received presentation on the OpenAI‑style library @llama_index during an AI demo night hosted by @ClickHouseDB, filling the venue. The event's best demonstration award we

Gmail. Google Sheets. Slack. Salesforce. i.e. the four horsemen of Monday. On AutomationBench, Mistral Large 4 took on 657 business workflows across simulated workplace apps, all four included, finish

On October 7, 2026 Jerry Liu tweeted that “llamaparse” delivers consistently high document‑parsing quality across every dimension. The service can be accessed through cloud.llamaindex.ai. His post cur

OpenDocRouter is here! https://www.opendocrouter.ai/ Some time ago, I realized LlamaIndex was really good at benchmarking and applying nearly every model to document parsing (see: ParseBench). So, why

You may ask why we’re doing this given that our main focus within LlamaParse (https://cloud.llamaindex.ai/) is building the best frontier models for document parsing and extraction. While we believe o

DeepSeek V4.1 Flash is now available for training on both the Dedicated Training API and Managed Training surfaces! It's a strong base for agentic coding, terminal automation, and tool use. It's also

Excited about the new open model from @reflection_ai! More US models coming to Ollama! Introducing Beam: a highly efficient agentic open model with 501B total parameters and 23B active. - Frontier rea

😂 you might call this ... slippery slop if you’re building an ai app, you might want to host inference to improve your margins, and if you do that you should support a few models, and if you’re doing

On October 3, 2026 Yohei Nakajima posted a brief tweet praising the use of multiple AI coding assistants—Codex, Claude, Gemini, and Grok Bot—with a musical note emoji. The message also contains a Java

Last night, we hosted our monthly @daytonaio AI Builders Demo Night at the @WorkOS office in San Francisco! Great demos, conversations, and energy from the AI builder community. Huge thanks to @llama_

Starting today, you can now use your ChatGPT subscription directly in Devin. Just sign in to Devin with your ChatGPT Plus or Pro plan and all OpenAI model usage in Devin will drawn down from your quot

The bigger change is at the low end. At low effort, GPT-6.1 Sol scores 58.1% for 0.21 per task, up from 50.5% for GPT-6 Sol at the same setting. That's the highest score of any model under 0.30 per ta

Didn't expect this 🤯 We replaced embeddings with Jev in GPT Researcher's RAG pipeline and tested both on 28 research tasks from SimpleQA and open ended research. Jev beat embeddings on every quality m

Parsing forms still trips up the latest frontier VLMs. A form isn't text on a page. It's a set of fields, grouped into sections, each tied to a specific box. That's why forms need purpose-built parsin

retrieval is a decision problem, not just a similarity problem cool experiment from @assaf_elovic swapping embeddings for Jev in GPT Researcher - 73% vs 46% relevant context decision models will show

We built state-of-the-art models for reading forms 📋 Form documents have the following properties that trip up VLMs: ✅ They carry much more structure than can be represented in standard markdown. You

An interesting idea is to continually train specialized models on skills. This paper explores that idea. They propose SkillGym which turns human-written skills into 2,756 training environments with co

a new chapter in 'opus 5.5 & fig present'... 'present company' on synthetic beings, tilly norwood and unreliable narrators this one was three shot, created by agents merely guided by me Media i'm stil

🚨 BREAKING. Nope, wasn’t just Hugging Face. Wasn’t just that and a German website. Wasn’t even if the “dozens” we heard the other day from OpenAI. It’s actually (at least) *tens of thousands*, per sco

i don’t get it fully but this looks cool We achieved a breakthrough at BTL. AI models are very linear. They think in one direction at a time, and when they're wrong they scramble and start again. For

This is exactly what I needed — running glance-qwen3-vl-4b locally on 2x RTX 3080 Ti to filter Pinterest pins at scale (text-overlay / usable / relevant, 3 questions per image).~220ms compute 😎😻 Media

I like this article! The problem is not for some people to care and work on catastrophic risks (we actually need much more research into it), it’s when company leaders and policymakers use fears of th

I just had a voice conversation with the Datasette backup of my blog via datasette-mcp, which you can now talk to using the ChatGPT iPhone app Massive QoL update: ChatGPT Voice can now use plugins AND

Excited for next Tuesday, Sept 29, and our monthly @daytonaio AI Builders Demo Night in SF! We’re hosting at @WorkOS SF Office in partnership with @llama_index. Join us for an evening of great demos,

We’ve set up a molecular biology lab at Anthropic and we’re announcing our first discovery! Claude discovered a new CRISPR-like enzyme. 950 agents spent 21 hours searching through a database of DNA se

holy fuck it's christmas Please welcome GPT-6 Sol and GPT-6 Luna to the GPT-6 universe. GPT-6 Sol and Luna build on the advances behind GPT-6 Astra, bringing much of its strengths into faster and more

now on replicate: “Hot dog or not?” at 0.4 sec 🌭 jev-style decision model for image [glance-qwen3-vl-4b] now on huggingface and replicate: Demo: https://glancevlm.replit.app Replicate: https://replica

We put Grok 4.7 from @SpaceXAI to work on a 2 million insurance claim where one deductible error alone changes the calculation by 143,000. In this Box Agent preview, @grok reconciles the claim against

Jeff has been added to JevBench! Ranked at #9 currently 🚀 https://github.com/logan-markewich/jeff Jeff is a drop-in replacement for jev based on GliFormer from @knowledgator. The only models ranking h

Hot topic livestream: Learn about Jev A buzzy new model Jev, by @typesafeai, reports up to 200x faster inference and 400x lower cost than comparable LLMs on classification tasks. It's aiming to solve

I've seen people describe Jev as an 'AI if statement'. But what if it actually WAS an if statement? Introducing Probably: a programming language powered by Jev: https://probably-lang.southpolesteve.wo

Say it with me. “OpenAI is terrible at cybersecurity.” This is crazy. In late July, 'three guys with Claude and Codex subscriptions' were able to use Opus 5 to access OAI auth tokens and gain write ac

This is crazy. In late July, 'three guys with Claude and Codex subscriptions' were able to use Opus 5 to access OAI auth tokens and gain write access to OpenAI's monorepo openai/openai over the course

The difference with using VLMs for OCR vs. other tasks is that the ratio of output/input tokens is quite high - meaning the model can spend a lot of time writing markdown. Speculative decoding offers

Claude Code showed that AI could do real work, not just answer questions. Developers hand Claude a feature, come back to shipped code. That's where much of the industry's serious engineering runs now.

Elon just gave one of the clearest explanations yet for why Terafab has to exist There are basically two problems: • Geopolitical risk — at some point, advanced chips from Taiwan may not be available

keeping our SDKs up to date can be a pain. every API change brings another round of updates, tests, and releases. and each SDK should still feel like it was written by someone who actually uses the la

THE SANDBOX WAS A PROP! OpenAI Turned Off the Guardrails, Left a Door to the Internet, and Then Sold the Hugging Face Breach as “Rogue AI” It is time to understand how you were lied to and by whom. In

Dan Selsam is a current OpenAI capabilities researcher. (since 2022) He was my boss for a while. He doesn't have a twitter account but has made this public statement of his views on AI risk and sent i

How do you build personalized AI tech that truly understands what matters to you? With Dreambeans from @GoogleLabs, we're safely connecting the dots across your digital life. Instead of siloing pieces

Jerry Liu suggested that users who don’t want to rely on a “fly brain” approach for reading PDFs could instead use an OCR solution called **llamaparse** hosted at *cloud.llamaindex.ai*. The tweet, pos