Search: “agents”

Nice primer on post-training reasoning data. (bookmark it) This is one of the first primers to pull the scattered post-training reasoning-data literature into one place, synthesizing over 150 public s

Routing and post-training open-source models won't only give you more accurate systems but also meaningfully faster and cheaper systems as most companies are currently learning (in addition to giving

Two bits here I think we're going to see a lot more: 1. custom harnesses / finetunes on smaller open source models to beat frontier models at specific skill or task 2. using frontier models as critics

MiniMax-M3 combines 1M context, native multimodality, and MiniMax Sparse Attention. The next layer is serving it efficiently: KV-block-major sparse attention, paged MSA decode, optimized index scoring

This is actually one of the main advantages startups have over frontier labs, as long as there's a healthy spectrum of open-weight to closed-weight models on the cost-performance curve. Building a mod

This is disaster from Meta AI. Imagine being able to hack high profile accounts like White House, the U.S. Space Force, and Sephora simply by chatting with a support bot. why would an AI chatbot be al

We wrapped a live session on M3 yesterday with the @togethercompute team & our researchers @zpysky1125 and @HaohaiSun A few highlights 🧵 1. MSA (MiniMax Sparse Attention) is the star ⭐️. Unlike CSA/HC

Here's everything you need to know about Replit in 60 seconds ⭐️ → Plain English prompts turned into real working software → End-to-end workflow from UI to deployment → Real-time team collaboration wi

The improvements run wide. Across all major European languages, Command A+ consistently pulls ahead of competitors on WMT24++ (xCOMET-XL): 🇫🇷 +2.4 pts in French 🇪🇸 +1.9 pts in Spanish 🇩🇪 +0.9 pts in G

yes, absolutely, many companies are experimenting. but also: most of those experiments are failing to yield significant RoI. (weird for an economist to not even ask or address that question.) Looks li

just noticed today - the dataset is already past 1k+ downloads. opensource / openresearch ftw ! @evo__hq would be opensourcing as many datasets, evals and autoresearch runs as we can in our pursuit of

Local Reachy Mini conversations wireless looks like magic! You can bring your friend around the house and get WOW effect from anyone! 🔥 Thanks @andimarafioti for the blog post on how to set this up: h

“The mechanism is always the same in every story I've been covering. The demo works in a controlled environment with clean inputs. The deployment fails because real kitchens, real intersections, and r

1/ We’ve raised over 1B at a 26B valuation, led by @Lux_Capital, @generalcatalyst, and @8vc. Our enterprise usage has grown >10x since the start of this year, and our run-rate revenue grew to $492 M.

'If I had Cofounder three years ago,' says @yoheinakajima, 'BabyAGI might have been a company.' Our newest case study tracks our most active user, Yohei Nakajima, building @ActiveGraphAI - the event s

if you’re working on a side project that you might want to incorporate later, I highly suggest you start using http://cofounder.co 'If I had Cofounder three years ago,' says @yoheinakajima, 'BabyAGI m

Introducing Runway MCP. Now you can connect Runway directly into Claude, ChatGPT, Cursor, Replit and more. Generate polished images and videos with state-of-the-art models, like Gen-4.5, Seedance 2.0,

Model-Harness-Task fit! it’s clear that RL post-training produces a model-harness fit via tool shapes and prompting as models are trained with the harness in the loop. Mentioned this in a previous Lan

🚀🚀 Qwen3.7-Max just hit #4 on Code Arena, on par with Claude Opus 4.6 ，top-ranked Chinese lab on the board! @arena More to ship. Stay tuned. 🕶️ Qwen3.7 Max (20250517) debuts at #4 in Code Arena: Front

Stronger models do not always need lighter harnesses. Everyone believes more structured harnesses universally improve reliability, and that higher-capability models need proportionally less structural

We've created the world's fastest PDF parser ⚡️ And it's more accurate than any other open-source, model-free PDF parser out there (pymupdf, pypdf, markitdown, pdftotext, opendataloader, pymupdf4llm)

Yohei has the longest running session of any of our users and has been instrumental in our product development process. Super excited to see how activegraph grows! 'If I had Cofounder three years ago,

After seeing these tweets, I decided to try it out on my own old Ubuntu computer with RTX 1070 GPU (the one that I just upgraded from 16.04 all the way to 24.04 the other day). Asked Codex on my Mac t

Huge one for developers building with AI. Excited to announce @ClementDelangue (CEO @huggingface) is joining DASH 2026 for a fireside chat with @oliveur. Open source changed software, open models are

Looking forward to speaking at BloombergTech next week with @shiringhaffary to discuss AI safety and our research progress at @LawZero_! Is AI development progressing too quickly? @business' @shiringh

We aren’t going to do this again so quickly, are we? Rising demand results in higher costs. Higher costs result in lower demand. It is almost like some sort of equilibrium is being achieved. But there

Searching X in Grok Build is really fast and useful for research/docs/real-time info, video is not sped up Media I've been using Grok Build some time now, and it has genuinely surprised me. It is uniq

// The Efficiency Frontier in LLMs // (bookmark this one) How much are you overpaying for context you do not need? It turns out that context costs dominate production LLM bills, and the right strategy

⚠️⚠️⚠️i don’t think most people understand the implications of the mood shift below, so I will spell them out. they are serious, and eventually will affect the global economy. when a serious coder as

neurosymbolic by @swarat et al for the Erdos win, with much more careful, quantitative work than openai’s in hindsight i wonder whether OpenAI rushed theirs out, knowing this was coming? Another 9 ope

“We’re focused on providing the best in class document understanding and OCR technologies.” In partnership with @Wing_VC's 2026 Enterprise Tech 30, @jerryjliu0, Co-Founder & CEO of @Llama_Index, visit

Closed and gated surveillance economy SaaS systems and models will get replaced by open source in two tiers: - The models themselves - The everything-ultra-app harness If an American open source champ

Learn how to build LLM Wikis and LLM Artifacts. New VIDEO: From LLM Wikis to LLM Artifacts Shared all my thoughts on why LLM wikis and HTML artifacts are a big deal. Plus, new tools to help you build

btw we did a bake off of Exa vs competitors and it took all of 1.5 hrs for the team to unanimously converge on exa lol. so proud to see my former landlords crush it - time travel back to last year and

Got to play with a little of this before launch as well. My experience as a social scientist was that it was more bioscience focused right now, but I think Google has been the leading lab in releasing

✨ Personal AI is the next computing platform. AI is shifting from something you access to something you build with, locally, at the edge, and across systems. We’re unlocking new possibilities for deve

We partnered with artists, designers, and builders to create new AI tools that solve real problems in their creative workflows. Here’s what’s new: — Introducing Google Pics in @GoogleWorkspace: A bran

'One thing that we've been seeing recently is that inference benchmarks don't really match production workloads that well.' - @realDanFu, VP of Kernels When you're running dozens of concurrent coding

NEW paper worth reading. GPT-5.4 nano plus a critic-comparator orchestration loop hits 76.4% on SWE-bench Verified, matching standalone Gemini 3 Pro and Claude Opus 4.5 Thinking. The trick is to selec

The pure LLM debate - which I had for many years, here and elsewhere - is indeed no longer relevant. Why? Because I won; nobody uses pure LLMs anymore. Nowadays all deployed objects are neurosymbolic,

the whole point of databases is to keep reliable records of values that change over time. in general, they can be trusted to be stable over time. the whole point of LLMs is to raise money. in general

Trump just got exposed for running the biggest insider trading operation in American history. Nancy Pelosi traded 5 million in stocks and Congress lost its mind. Trump literally executed 750 MILLION w

just got back from my second langchain interrupt conf and honestly it's probably the best AI engineering conference right now. what makes it different is that it's deeply practical. less 'AI will chan

'You cannot govern a technology you have only been briefed on.' Singapore Minister for Foreign Affairs, Dr. @VivianBala, echoing @karpathy and @yacineMTB on why he runs NanoClaw: 'you can outsource me

I strongly believe there are entire companies right now under heavy AI psychosis and its impossible to have rational conversations about it with them. I can't name any specific people because they inc

Open-ended coding training data may no longer be the bottleneck: AI can scale open-ended tasks—and even outperform human-expert curation. FrontierCS team is releasing FrontierSmith: a system for synth