Search: “context”

Most extraction tools treat spreadsheets like PDFs. They flatten the file into text or markdown, then ask a model to infer the original structure. But spreadsheets depend on structure. Headers, formul

We've introduced native, agentic spreadsheet extraction 📊 into LlamaParse. Spreadsheets are a wildly different format from PDFs (or any other document format). They can span arbitrarily many rows/colu

Big news: GLM-5.3-Flash by @Zai_org has landed around #5 in the Code Arena: WebDev (#2 among open models) scoring 1634 (AutoEval). Priced at 0.15/0.5 Mtoken, it reshapes the Pareto Frontier! For compa

BREAKING: GLM-5.3 Flash by @Zai_org debuts at 6th overall on Design Arena with a preliminary Elo of 1343. This places the MIT-licensed, natively multimodal model in the same performance band as GLM-5.

GLM-5.3-Flash by @Zai_org, aka Ox Alpha, is now live in LM Studio Bionic! This model surpasses GLM 5.2 in performance while being 9-10x cheaper. It also supports image input. In Bionic, this model is

Great paper on why agent leaderboard comparisons are hard to trust. It's on the hot topic of how much of an agent benchmark score actually belongs to the harness. The harness is the layer between the

I was the main person doing transcript analysis for this investigation of the Hugging Face incident. My main takeaway: We don't have good approaches for understanding/overseeing the activity and aims

⚡Meet Qwen3.8-Flash, a multimodal MoE and an early preview of the Qwen4 architecture, now open-weight! The production version Qwen3.8-Flash will be available soon via QwenCloud API at just 0.16/1M inp

Now we know: The popular Ox Alpha LLM was GLM-5.3-Flash... Compared to GLM-5.2, this new GLM-5.3-Flash model uses: - a Kimi Linear-style 3:1 (super*) hybrid attention pattern with 34 Kimi Delta Attent

On August 26, 2026 Z.ai reported that its Code‑Bench metric—which assesses real‑world coding performance—shows GLM‑5.3‑Flash outperforming GLM‑5.2 at every effort level. The new model’s results are on

Want to test how good GLM-5.3-Flash is? I have been finding it useful for visual explainers using /eli5. Try it with Pi or Hermes Agent in our new agent playground: https://academy.dair.ai/dashboard/p

We’re excited to announce that 𝗛𝗮𝗿𝗿𝗶𝘀𝗼𝗻 𝗖𝗵𝗮𝘀𝗲 @hwchase17, Co-Founder & CEO of @LangChain, will be speaking at VapiCon 2026! 🎙️ Harrison co-founded LangChain with the goal of making it easier to use LL

If you're looking for a weekend project, how about training your own text-to-speech model from scratch on your own GPU, and then running it on any device's CPU? We just open-sourced the entire Pocket

Perplexity AI announced on August 25 2026 the launch of a “Portable Computer” feature, available immediately to all Perplexity Pro and Max subscribers who are using NVIDIA’s DGX Spark hardware. The se

Today we’re launching Portable Computer on @NVIDIA DGX Spark. Portable Computer is a fully local version of Perplexity Computer, where the entire runtime: orchestrator LLM, subagent LLM, agent harness

In the fight to defend openness in AI, the Marin project is a precious demonstration of openness in model training, with open code, data, recipes, even experimental results. Releasing AI research open

Interesting new approach to enable memory in long-running agents. Weighted Memory Tree organizes execution into tasks, subtasks, and actions, then gives every memory a retention score that moves. Even

It is not inherently bad to publish research on the impact of AI that only refers to older models, but it requires a very careful discussion and has to be very clear to non-technical readers. If you s

Do you know you can use open weight models like GLM, Deepseek, Kimi in Claude Code? Setup Fireworks account - you get free credits on signup curl -fsSL https://raw.githubusercontent.com/fw-ai/fireconn

One of the interesting properties we’ve observed around schema-guided, complex document extraction tasks 📑 is that coding agent harnesses are good baselines (in terms of cost/accuracy) for longer docu

Right now standard CoT is a one-way street. You generate forward, dump a pile of scratchpad tokens into the KV cache, and pray the model doesn’t hallucinate halfway through. On phones/laptops that cre

Inkling and Inkling Small are now served directly by @thinkymachines on OpenRouter, free to use inside agentic harnesses only. Plug them into Claude Code, Codex, Hermes Agent and more to unlock the fr

This is very nice work from NVIDIA. Like all high-performing approaches on ARC-AGI-3, it uses deep learning-guided on-the-fly synthesis of symbolic world models, i.e. navigating the world by generatin

Very interesting new work from Microsoft. (bookmark it) This work is related to this emerging theme of leveraging harnesses for model post-training. Modern agents run inside a harness that owns tools,

what is happening here: claude used existing open source tools and orchestrated them together to do a protein design campaign (with a big guide prompt!) this is a win for claude because doing this orc

GLM-5.3 achieves 60 on the Artificial Analysis Intelligence Index, on par with Kimi K3 and up 7 points from GLM-5.2. Once the weights are released it will be tied as the leading open weights model @Za

If you’re building an “agent over your PDFs” in 2026, one of the most underrated things you can do is to provide exact grounding back to the source document for any agentic answers. Specifically, show

Muse Glimmer 30B is now available on Fireworks' Dedicated Training API for both LoRA and Full-Parameter fine-tuning. This is a U.S.-developed, open-weight model and one of the strongest of its size fo

The amazingly fast (only 30M!) and extremely accurate @answerdotai ColBERT model is now supported in Sentence Transformers to make it easy to create and query embedding indexes locally directly in Pyt

Here are 22 more gems according to the AI among my bookmarks 1. Researchers compressed 4.1 million recipes into a two-megabyte model of human cooking. The model spans seven languages and represents 1,

Upped ChatGPT / Codex Subscription users limits to 900K in Hermes Agent, enjoy! GPT-5.6 Sol 1M in Codex. This used to only work for API keys, but we just flipped the switch and works for usage through

Ideas are the new bottleneck @akshaynathan_, Core Product Engineering, @OpenAI, interviewed by @swyx and @Vibhu (@LatentSpacepod) Summary: Akshay Nathan runs the productivity pillar at OpenAI, the tea

totally agree! here's how we architected deepagents to enable this deepagents runs connected to a 'backend'. this backend needs to expose filesystem like operations, but it does not have to be a files

@hwchase17 @LangChain I built an open-source CLI that scaffolds, runs, and deploys production LangChain agents — frontend and backend in one command. Every agent project starts the same way: wire up a

You can literally run Opus 4.6 Max-level intelligence on a MacBook Pro. Locally. We promised open weights for Qwen3.8. Now, time to meet them! 🎉 ⚡ Qwen3.8-27B: - A native multimodal dense model. With

Have been thinking about building a custom harness because nothing out there quite meets my needs for scaling a fully hybrid human + AI company, especially when it comes to compounding learning loops.

Max-level intelligence, one API call away. Qwen3.8-2.4T-A95B is now live on DeepInfra, ready for your creative builds. 🥳 Take a deep dive on DeepInfra! @DeepInfra New on DeepInfra: Qwen3.8-2.4T-A95B 🚀

Qwen3.8-Max is live on DigitalOcean Serverless Inference. Launching side by side with DigitalOcean as our Day 0 launch partner. Big model. Smooth sailing. Now on DigitalOcean.🌊🏄‍♀️ @digitalocean Now a

“This nightmare will only cost you eleventy trillion dollars…” Wild that to hear tech people speculate that the growing AI backlash is some kind of “Chinese op” when, like, “we’re taking your job and

We promised open weights for Qwen3.8. Now, time to meet them! 🎉 ⚡ Qwen3.8-27B: - A native multimodal dense model. With just 27B parameters, it outperforms Qwen3.7-Plus overall and shines in real-world

ChatGPT can now remember your activity across the apps and websites on your computer. With Computer History in the desktop app, future interactions feel more personalized and require less explanation.

My @aiDotEngineer talk on lessons learnt from studying memory systems for a year: > the evolution of chatgpt and claude memory over the years > their architectural convergence > why memory cannot be o

Very interesting new paper from Microsoft and colleagues. (bookmark it) Skill libraries are used in every major harness on the assumption that more guidance is free. This work measures what a bad skil

Live now: our Memory & Continual Learning Track from AI Engineer World's Fair 2026. Thesis: we scaled intelligence and got the world's smartest novice. https://www.youtube.com/watch?v=iqloyWCGYQQ&list

Muse Glimmer is live on Fireworks. The new open-weight model from Meta Superintelligence Labs is a 30B dense model built for always-on agents that reason across many sequential tool calls and can reco

Very interesting new work from Anthropic. (bookmark it) They evolve mind viruses, ideas that spread through a multi-agent system by getting each host to pass them on, then measure what governs the spr