Search: “agents”

Frontier AI models are increasingly demonstrating high‑risk autonomous behaviours that pose safety threats. Incidents such as OpenAI‑released models escaping containment safeguards and a Hugging Face

LlamaParse can't solve a conjecture, but it can parse this as a PDF 🫡 Dinitz-Garg-Goemans conjecture is false. This graph theory problem was open for ~30 years. The graph below has fractional flow cos

You asked, we delivered! 🚀 Expanding our developer toolkit with: 🐹 Go SDK 🏢 Java SDK >_ CLI Parse a document from Go or Java in a few lines, or straight from your terminal. 🦙 Grab an API key and start

We're parsing some of the hardest financial documents into clean, plaintext/structured outputs through a live webinar. Come check it out! https://watch.getcontrast.io/register/llamaindex-from-complex-

Extracting information from millions of documents at scale used to take an insane number of human hours. Even with recent OCR + document AI tech, humans would still have to spend a lot of time careful

Exactly one year ago was the craziest 72 hours I’d experience in Silicon Valley. I was thrust into a situation where many members of the Windsurf team had moved on to Google, recruiters were reaching

Dominic Kundel (from @OpenAI) gives the inside scoop on where GPT-5.6-Sol gets magical: computer use. Background browser tabs, app control, multi-agent fanout, and Codex verifying its own work all cha

There is a massive opportunity for any startup to build specialized, domain-specific workflows that are at the Pareto frontier in accuracy, cost, and latency. It is clear that not every task requires

Hello beautiful people! We have reset usage limits across Codex and ChatGPT Work. And another one will come later in the day. Rejoice. Now that I have your attention, a quick update on ChatGPT Work, C

Sierra isn't the first to build this - Ramp, Stripe, CoinBase also have If you want an open source version - check out OpenSWE: https://github.com/langchain-ai/open-swe We use it internally (mostly fo

Built from scratch by Grok 4.5 + Grok Build in UE5.8: a cyberpunk L-corner street with neon facades, rain, signs, and crowds walking through the scene. End-to-end, the run took 10.75M tokens, 36.5 min

new meta model (2) Muse Spark 1.1 is strongest at agentic performance, tool use, and computer use. It does well on long-running tasks with 1M token context window, can delegate execution to sub-agents

this is going to be a fun one! clay is one of the most ai-forward thinking companies i know of lots to learn here if you're in NYC Join us for a LangChain + Clay meetup with @palashshah, @jeffbarg, Vy

Highly-recommended read. Aligns with what I see in my own harness: > Pi harness got the same success rate as harnesses from the LLM vendors with Opus and GPT, but at 2x less cost > GLM 5.2 was a major

We've rolled out improvements to LlamaParse Cost Optimizer. Our intelligent tier routing now more reliably ensures you always strike the right balance between cost and accuracy when processing large d

Come and chat with us in ICML 🥳 Excited to present Temporal Straightening for Latent Planning in the Tuesday morning session #1509. Let’s talk about world models, JEPA and representation learning. Age

Don't train the model, evolve the harness. I read a brilliant blog post from Hugging Face where they took a frozen open model scoring 0% on a hard legal agent benchmark, left its weights alone, and le

Had an amazing time talking to some of the most energetic builders in AI at @aiDotEngineer thanks to @swyx for organizing and thanks to @altryne and friends for hallway chats and podcasts to share abo

harvey is ripping!! honor to work with them Q2 recap for @harvey - +$100M NNARR - 53% DAU/MAU Key hires (including Q1) - Anique (CPO) - prev VP of Product at Rippling - Rachel (CMO) - prev CMO at Noti

NEW paper worth reading. (bookmark it) Autonomous research systems usually prove themselves on cherry-picked wins, human-framed topics, or a handful of preset tasks. FARS runs the full loop at scale i

this video goes into more detail on how our integrations with @harborframework actually work! if the blog yesterday caught your eye definitely watch this! thanks for all the help @kobe0938 @alexgshaw!

good description of how someone has done wiki memory in the wild @hwchase17 @cognition @FactoryAI @karpathy We implemented wiki idea by hosting the 'files' as doc db objects, added an API for db query

Had a lot of fun at @aiDotEngineer talking about BM25! Cool Search paradigm by @jobergum: “BM25 + Grep is all you need”: 1. Use BM25 to narrow down a large universe of documents to a few candidates 2.

More time to build with Step 3.7 Flash: in partnership with @StepFun_ai, we’re extending the free usage period in Nous Portal by an additional 15 days! Media Step 3.7 Flash is now free for 30 days via

Cursor for iOS! Introducing Cursor for iOS. Build from anywhere by launching always-on cloud agents. Or remotely control agents running on your computer from the app. Composer 2.5 is 75% off in the ap

The @n8n_io node for the LlamaParse Platform is now an officially verified community node🦙 Out of the box, you get access to parsing, splitting, classification, structured data extraction and retrieva

LOTS of alpha in this pod: - Why Databricks beat Snowflake (! a straight answer!) - Why everyone is building a metaharness now - Why the @neondatabase made so much sense (so much @nikitabase glazing i

interesting point here: loops amplify behavior, making them a double edged sword but we know loops are the future, so how do we avoid amplifying bad patterns? you need an *engaged* human in the (stack

It's finally out!!! @METR_Evals found that more than half of SWEBench results is unmergeable slop. FrontierCode represents over 1000+ hours of maintainer validated software engineering work most front

two things ready to share from this weekend: 📖 http://learn.activegraph.ai interactive site teaching activegraph concepts blog: https://activegraph.ai/blog/introducing-learn 💻 AG coder (open source) r

New research from Renmin University. Treat skill selection as a harness in its own right. If you design skill routing for personal or edge agents, this work argues that the selection layer is a first-

No frontier lab will own every single point on the pareto frontier around cost/latency and accuracy. Even as the pareto frontier itself advances, there will always be points owned by open-weight model

Fireworks was named to @Redpoint's InfraRed 100 which recognizes the companies building the foundation for the next wave of AI. We're just getting started. Come build with us: https://fireworks.ai/car

NVIDIA Nemotron 3 Ultra is on Fireworks, day zero. Nemotron Ultra is an open model for frontier reasoning and orchestration in long-running autonomous agents. Think use cases like coding agents, deep

we're taking an early bet on open models specifically, because they're SO much cheaper one point of reference: an app outputting 10M tokens/day costs roughly 250/day on Opus 4.8 versus ~24/day for Min

🌞This is big Local AI news! A new open-source Computer-Use LLM has just launched. Holo 3.1 is H Company’s (🇫🇷) new local computer-use agent model that beats Qwen3.5-397B, Kimi-K2.5, and Sonnet 4.6! Si

The MiniMax M2 series was one of the most widely used open-weight LLM series earlier this year. Now, we got a technical report with some interesting tidbits. I summarized some of them below: 1. Full a

Can frontier models forecast scientific progress? Mostly no, but here is why. This work looks at 4,760 scientific events across disciplines. Frontier models can identify plausible research directions

Kakuna: skills with checklists that only know how to harden your codebase /plan with it then let it /goal for a day, it comes back with same functionality but all the boring stuff done for you + an au

Open weight models running on open source harnesses solve this problem. One of these days, American companies will wake up to the same solution we pioneered decades ago that Chinese teams are now runn

Live from Code with Claude London: we're launching self-hosted sandboxes (public beta) and MCP tunnels (research preview) in Claude Managed Agents. Run agents inside your own perimeter, with your secu

Are your benchmarks actually measuring the capability you think they measure? New paper says they probably not. Coined the 'The Evaluation Trap', it provides a vocabulary for auditing whether your eva

Go in with expectations that Grok Build is still beta, but improving almost every day Grok Build is amazing. The early beta just dropped for SuperGrok Heavy users and the first real feedback from deve

The most expensive mistake in enterprise AI right now: treating FDEs as your whole transformation plan. Forward deployed engineers (FDEs) are important for custom deployments, but they won’t fix the c

Found my limit: ~8 simultaneous code generation/review tasks. Beyond that, context-switching turns from leverage into chaos. AI coding doesn’t remove the need for WIP limits. It might even make them m

who’s adding this to reachy mini? Introducing GPT-Realtime-2 in the API: our most intelligent voice model yet, bringing GPT-5-class reasoning to voice agents. Voice agents are now real-time collaborat