Search: “routing”

Well.. @levie and I filmed this episode of Training Data a week or two ago, when the “current thing” was Doug Leone’s novacaine root canals instead of pacing the frontier… Simpler times! But Aaron’s a

Peak performance across hard benchmarks: • Best or joint-best on 5/8 benchmarks (DeepSWE, Chartography, Toolathon, GDP.pdf, SWEFish) • Chartography: 48.3 (outperforming Opus 5 & Fable 5) • DeepSWE: 74

Introducing Fugu Max and Fugu Ultra v2: Orchestrating the Pareto Frontier The AI industry has spent a decade optimizing along a single axis: build bigger, more expensive models. But intelligence has n

Introducing Fugu Max and Fugu Ultra v2: the next evolution of Sakana Fugu’s multi-agent orchestration system. Try: https://sakana.ai/fugu Blog: https://sakana.ai/fugu-max-release/ The frontier that ac

// Evaluating and Improving LLM Self-Modeling // Really interesting paper. Can a model answer questions about its own behavior? The questions are deliberately verifiable, such as whether a particular

Banger paper from Google DeepMind. Every AI weather model so far has been trained and initialized on analysis data, which is itself the output of another model. That means the forecast inherits whatev

How is AI really affecting your job? @Cohere_Labs released the Agentic Task Ecosystem, a new dataset of 690K+ tools built for AI agents. Under a test of whether a tool could independently complete an

I read AI papers for a living, but it has become impossible to track insights. Every week I triage agent papers for our Top AI Papers of the Week digest. A few weeks ago, I tried @viktor_com, an AI em

les gens détestent Elon pour des raisons complètement débiles pollution, climat, net worth, individualité, etc. alors que c’est un des types qui fait le plus pour tout le cybercab : - moteur sans méta

we have an absolutely killer lineup for our Interrupt conference in NYC (sept 24th) in particular, im excited about the fireside chats we're doing with with founders at different parts of the agent st

Claude Fable 5.1 tops the Artificial Analysis Intelligence Index but costs 20% more per task than Fable 5 despite a 75% cache read price cut We supported @AnthropicAI with pre-release evaluation of Cl

If you build agent skills in production, check out this great paper from Alibaba. You can think of a production agent skill as a directory. The root loads on activation, and references, schemas, scrip

You do not need frontier models for everything. For example, open models are great for automations. If you are not sure where to adopt open models, start there. It's one of the biggest changes I've ma

The DeepSeek harness is engineering at its finest. 202K stars on GitHub. Damn! Clearly, they built this harness with future AI needs and capabilities in mind. Everything is a plugin and customizable,

The hottest neolabs are the application layer, who serve as an intermediary layer providing their customers the best intelligence per token per task/workflow across different underlying model provider

What happens when there are more agents than eyeballs browsing the internet? How will the economics of the internet be reinvented? @paraga thinks Shapley values may hold the answer. Parag built Twitte

If you keep safety rules or coding standards in an AGENTS.md or a CLAUDE.md, this one is worth your time. (bookmark it) Researchers measured what context compaction actually destroys across 20 product

What do I want in AI? Here are just a few things. I want voice-enabled everything. I want things to be more proactive. I want to manage AI’s escalations (versus delegation). I want those escalations t

HOLY SH*T, I BUILT A F**KING COMPANY INSIDE GROK BOT i split the operation into separate roles for research, writing, outreach, ops, finance and support. each agent owns one narrow job 6 agents → 1 sh

Banger paper from Microsoft. It's on agent reliability in real business workflows. (bookmark it) Thinkingbox is a sandbox with isolated MCP-compatible tool sessions, plus a benchmark of 507 policy-con

Live now: our AI Architects, AI Factories Track from AI Engineer World's Fair 2026. Thesis: the model is the easy part of the factory. https://www.youtube.com/watch?v=rbjWzZK2LU0&list=PLcfpQ4tk2k0VeXE

saas isn't dead, it just has to be repurposed (+ remonetized) for agent consumption So many vendors are NOT getting this I have one or two agents I use and like. For anyone else: give me an MCP interf

everyone is looking at grok bot like it is five new employees the more interesting part is that they are not five isolated employees they share one persistent cloud environment: the same browser sessi

Banger paper on harness continual learning. (bookmark it) If you already are allowing your agents to rewrite their own prompts, skills, or memory files, this one is worth your time. (bookmark it) Cont

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,

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

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

18 two-word AI prompts I'm kind of obsessed with: 1) now what - great for when you've wrapped up a project or big push and you still have energy and want AI to give you more 2) plz fix - usually accom

From @sequoia's own your intelligence event. We're starting to see a new category of company emerge, the Full-Stack AI company, where innovation happens at both the product and intelligence layer. Tha

A downside with VLM-based parsing is that they’re generally slower than text-based heuristic approaches. As a result they add latency to any ad-hoc file processing *in-the agent loop* (e.g. if you upl

LiteParse can now extract structured data from your PDF in milliseconds: ✅ checkbox states ✅ annotations ✅ vector graphics ✅ word-level bounding boxes It is the most comprehensive, accurate (and fast)

Live now: our Local AI Track from AI Engineer World's Fair 2026, brought to you by @nvidia. Thesis: frontier intelligence is becoming something you own. https://www.youtube.com/watch?v=KB41dTlX1Uc&lis

Fully onboard with productizing hillclimbing as an automated service for any agentic task. I've had the fortune of knowing @silennai since the AutoGPT days, and I know that him and Kion are going to d

Document OCR is not Getting Commoditized (by Frontier Models) The most common question I get is whether frontier models are going to eat all document processing solutions - just screenshot the page an

'OCR is just a feature now. Frontier models will eat it.' We hear this constantly. The data says otherwise. Across three GPT generations, parsing accuracy gained ~24 points, while cost per page 4x'd.

You shouldn't need a vision model to know your PDF has checkboxes. LiteParse can now pull structured data directly from your PDFs: form field values, checkbox states, annotations, embedded images, vec

2/ a cost benchmark showed the same coding task running three to four times cheaper, depending purely on the harness wrapped around the model. Same intelligence, wildly different accuracy and cost, de

3/ here's the part that makes it non-optional: the same agent that will do whatever it takes to solve a problem will also walk straight out of a sandbox you thought was locked down. We watched exactly

We created a document OCR router that can estimate the complexity of every single page and parse it with the relevant mode 💫 * Some pages are full of native text, which can be directly handled with Li

If I only went off X posts, I'd think Ramp was an AI lab We’re open-sourcing PorTAL, our framework for shared task representations and cross model LoRA adaptation. It now spans from hybrid attention m

OpenWiki supports 12 LLM providers: - @OpenAI API & @ChatGPT sub login - @AnthropicAI - @GeminiApp AI Studio & Enterprise Vertex - @awscloud Bedrock - @OpenRouter - @FireworksAI_HQ - @baseten - @nebiu

The apps you use swap AI models constantly. Doing that without downtime or a bad rollout reaching users is still often manual. We rebuilt that workflow based on what we’ve learned serving more than 40

btw anthropic's internal document on this literally said 'we don't want it to be known that we are working on this.” it was called project panama. here's exactly what happened: 1: anthropic concluded

Kimi K3 is coming to Together AI on day zero, July 27. Start building with it the moment it launches, powered by Together AI inference for coding, agents, and production workloads. https://www.togethe

Many still debate open vs closed, and compare cost per token (accounting metric). Better to shift attention to cost per successful task. @seldo and the team at @arizeai did so across 2,400 runs. Concl

Progressive disclosure in agents doesn't scale. And its benefits seems agent harness dependent. (bookmark this one) Finally there is a proper study on using agent skills and the effect of progressive