Search: “routing”

New open-source agent harness just landed! I got early access to TrueForge by TrueFoundry and have been running it locally for the past few days. The harness layer deserves as much attention as the mo

Really interesting paper. I recommend it to anyone interested in training agents using existing harnesses. (bookmark it) ClawGym II runs RL through OpenClaw and Claude Code as opaque boxes. A serving

teams want to understand what their agents are doing but it’s hard to sift through all that trace data at scale but you can basically find any signal by fine-tuning a small, cheap model on data showin

Computer History builds on the Chronicle research preview with reduced token usage and more privacy controls. A new timeline view gives you the ability to look back on your work and build skills from

We are going to see a lot of vertically focused AI native companies accelerate. Routers, open-source models and specialized post-training enabled by companies like @FireworksAI_HQ have all made dramat

Not every page in your PDF needs the same treatment. A scanned cover, a dense table, a clean text page, a figure-heavy diagram.... most parsing pipelines throw all of them at the same parser, forcing

Situational Awareness, the $20bn hedge fund founded by former OpenAI employee Leopold Aschenbrenner, has sought to raise fresh capital from investors after suffering heavy losses during the recent rou

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

You don't need heavyweight VLMs to OCR simple text-only PDFs. Doing that is like bringing a bazooka to a knife-fight, and is completely unnecessary and worse quality than a tuned OCR approach. Output

spending the last week at @aidotengineer was awesome. too many great convos to cover them all, but jotted down some things that stood out: - Lots of discussion around open source models. I spoke with

Up until yesterday, our entire MTS team has operated under the philosophy of tokenmaxxing as much as possible on Claude Max plans. With Fable, this may no longer be possible: - One of our team members

Super-powerful AI models will launch in the coming weeks. We are looking at a potential step change in model capabilities. The biggest mistake right now is to lock into one vendor. I say this not only

Almost everyone is building agent harness systems the wrong way. The default move: pick LangChain or LangGraph or the OpenAI Agents SDK, accept the loop, the tools, the memory, the orchestration, the

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

System scaling is the next real bottleneck in agentic AI. If you build agent orchestration layers, this is a clean map of where the engineering leverage actually sits. The labs own the model. You own

NEW paper worth reading: MetaCogAgent MetaCogAgent equips a multi-agent system with metacognition so each agent decides whether it should answer or delegate. In other words, it aims for self-aware tas

THIS GUY LOST 200 IN ONE DAY BECAUSE THE STRING 'HERMES.md' WAS IN HIS GIT COMMITS HERMES.md is a real convention used in AI agent projects. it's a system prompt specification file. not some obscure e

Attending #AIDev26 by @DeepLearningAI? Join @AI21Labs, @trychroma + @Baseten for a panel on optimizing modern AI systems. Drinks. Nikkei food. No fluff. April 28 | 5PM | Kaiyō SF Register → http://lum

1/5 When we saw our Reducer (=LLM judge component in Maestro, our agentic framework, that selects the best output from parallel agent runs) consistently picking gold patches, we were sure Claude Opus

I was unable to retrieve the content of that specific X (Twitter) post, as web search results did not surface the tweet or its content. X.com posts are generally not indexed in a way that makes the...

AI Gateway now supports team-wide Zero Data Retention (ZDR). Building safely with multiple AI models means wrestling with fragmented data policies, per-provider negotiations, and the hope that develop

New paper from the team at Sakana AI: Recursive Self-Improvement through Multi-Agent Self-Supervision (MASS) How do we keep improving AI when the tasks become too complex for humans to reliably evalua

good framing from @ch3nweiii - a lot of agent steps are yes/no calls, not generation Jev answers those as typed questions with calibrated probabilities, so the frontier model sticks to the hard work w

OpenDocRouter is basically OpenRouter for document OCR You can compare and use all your favorite OCR models under a single API / billing interface. They range from some of the lightweight/OSS models (

3 helpful agent use cases that function like an EA and only require calendar access: 1. Email filter: junk signups go to your agent's email address. It reads everything, and you only get recaps of the

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

Today I’m excited to introduce OpenDocRouter - a unified API for document parsing with the latest frontier and open-weight models. There are a lot of VLMs and OCR models that can be used for document

Jacob Coxon @hilbertspaess and @DKokotajlo next at the NYC City Council meeting, hosted by @SpeakerMenin. Coxon cpens with “We do not know how to control any AI system yet”, which, importantly, isn’t

OCR is dead 🪦 Long live agentic OCR! Traditional OCR makes one pass and hands back whatever text it got. Tables get flattened, charts disappear, and multi-column layouts come out scrambled. Nothing ch

So much reporting on the Claude or OpenAI usage of the same handful of technology companies with competing products & huge cloud infrastructure of their own. There are many, many more firms out there

we're seeing our coding agent costs decrease significantly for second month in row longer blog on this later, but three quick steps we took 1/ cost visibility. you cant control what you cant measure.

Clef Decision Models are now on @ollama introducing 𝚌𝚕𝚎𝚏: our first models trained by @cloudflare's workers ai team. today, we're releasing two fast and accurate decision models that top the benchmark

This Week in Replit 1) Interactive charts are now in Replit chat. Why is this quarter's pipeline falling short? Which channels are performing best? Just ask Replit Agent 'let's visualize this' and get

Today we're unveiling Trillium Labs @trillium_labs, a new non-profit to foster the open science of frontier AI. We're building open post-training recipes and will expand into open infra to study RSI,

The user expresses enthusiasm for the decision‑modeling approach introduced by @typesafeai’s JEV tool, emphasizing a preference for local deployment to protect sensitive data. After learning that @oll

PDFs aren't built for machines: text shows up as glyphs with coordinates, tables as line segments instead of table structures. @jerryjliu0, CEO of LlamaIndex, digs into what that means for AI agents i

System one models are extremely useful for a variety of document tasks that require fast decisions: * orientation detection * language detection * classification * splitting We benchmarked Jev with ot

We've partnered with @OpenAI to bring the new Sign in with ChatGPT experience to Nous Portal. Log into Nous Portal with ChatGPT to use your plan in Hermes Agent, with full visibility and controls in C

Yann LeCun's lab borrowed a trick from the human brain and more than doubled how often an AI found its way to a goal. The paper is called Temporal Straightening for Latent Planning, from NYU with Brow

Banger report on building faster memory for AI Agents. If your agent's memory layer is slow, this design is worth a look. Great weekend read. It proposes a new agentic memory architecture, Jev-Mem, in

Pay attention to System One models if you are building custom harnesses and agentic workflows. Great to see DSPy integrate Jev and now support System One models for calibrating agentic workflows. I'm

Opus 5.5 is the best frontier model for parsing tables in PDFs. We ran it through ParseBench, and it scored 93.9%, a 7%+ increase over Opus 5, and beating Fable/Gemini/Astra. It's comparable to LlamaP

StepFun’s new Step 5 Preview model is impressive! Had a chance to test it early. I've been testing it as a coding agent. It’s on the Pareto frontier for cost vs. capability. It is a very capable model

Been integrating Jev into my custom harness. I couldn't be more excited about the results I am seeing. Most demos on my timeline are flashy but very basic. Notice they are all about some boring classi

Weekend project, getting AEO-pilled. Also a good test (for me) of Claude Projects. Have been meaning to update Eleventy and do a few other redesign tasks on https://cybercultural.com, which tbh has be

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