Search: “routing”

This is what strong inference economics unlock. @rox_ai built its own search agent, ran it in production for 6+ months, and reached 91.3% accuracy at 1.03¢ per query. Together AI is proud to help powe

🥉 3rd place: CashFromChaos, by David Diaz (@davddiazm) CashFromChaos starts from a single seller input and automates everything up until a completed sale. You send a photo and a one-line clue, and Her

Big unlock for open-source AI inference: Hugging Face Transformers models can now run in vLLM at native speed, often matching or beating hand-written implementations. Until now, every new architecture

We just shipped a full revamp of the RunAnywhere apps. iOS and Android, live now. One assistant, fully on-device, works offline: - new UI, opens straight into chat - device-aware model recommendations

Come help us scale @harvey’s model training team. If you’re interested in bringing frontier agent research into the Harvey product and working with: - @baseten to scale up RL to 80M+ token virtual dat

arXiv:2606.12502v2 Announce Type: replace-cross Abstract: We propose that value -- the quantity goal-directed agents create, destroy, and exchange -- is a lawful structural quantity in the same catego

Bridgewater just published numbers that should make every frontier lab nervous. The world's largest hedge fund tested Gemini, Claude, and GPT on six document filtering tasks its investors do every day

Frontier open models with enterprise governance means rebuilding workflows from scratch. Move faster with Fireworks on Foundry. GLM 5.2 is live on Microsoft Foundry. With FireConnect enabled, devs can

Fully solving document parsing includes covering every point on the Pareto curve of accuracy, cost, and latency: 1️⃣ High-accuracy parsing - requires 99%+ accuracy, price insensitive. Especially relev

Watch Devin Fusion work: The sidekick model handles fetching information and skimming sources. The frontier model makes a plan for implementation, then delegates well-scoped sub-tasks to the sidekick

the future of AI is multi-model (including a majority of open-source ones provided by @huggingface of course!)! How to keep AI spend flat while token usage grows exponentially: Not with friction and s

> Better Caching – Cache misses are the easiest way to drive your cost up. All of our requests are cache aware, so we’re reusing a warm cache wherever possible. We do this for you in Deep Agents - see

UBS says 60% of companies now watching AI budgets are moving to cheaper models and open-source Chinese models The pressure is coming from extreme bills, including users spending up to $35K/month, team

📣📣 Meet Qwen-AgentWorld — a native language world model that simulates 7 agent environments (MCP, Search, Terminal, SWE, Web, OS, Android) within a single model. Environment modeling is the training o

SpaceX's @Starlink will be installed on more than 80 giant Oldendorff ships. Oldendorff is one of the world’s largest dry bulk shipping companies. 'With vessels operating in diverse regions and tradin

C’est elle qui a jeté Fauci en pâture relayé ensuite par RFK et Musk… Je vous le dis Le RN au pouvoir ça sera ça. On peut ne pas être content. Vouloir du changement. Mais le changement ça peut être en

Another new idea to push the state of AI architectures forward. Sakana released a model that effectively uses a mixture of models to get work done. You get a single API but then the work gets farmed o

Fugu stands shoulder-to-shoulder with leading models like Fable and Mythos across the industry's most rigorous engineering, scientific, and reasoning benchmarks. Read the full blog: https://sakana.ai/

Human intelligence is fundamentally a collective intelligence. We solve complex problems by participating in a vast cultural network that builds upon ideas across generations. I believe the strongest

This ComfyUI workflow lets you draw lines and annotations to guide motion, define where actions should happen, and influence movement throughout a scene. An integrated LLM translates those annotations

completely agreed. cost management was not a priority prior to ~opus 4.5, but it's pretty clear there's a divergence between what frontier labs are optimizing for and getting real ROI in production th

Good take My guess is - demand for intelligence is near infinite - but 80% of workloads will be running on 99% cheaper models within 12-18 months - 20% of workloads will still run on latest gen models

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

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

If your daughter needs tutoring in algebra, you can probably find someone cheaper than Albert Einstein. Giving every task to GPT5.5 or Opus 4.8 is overkill. Often times you can get the task done just

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 post likely describes a tool or system for planning autonomous drone flight paths, possibly involving visualization or interactive path-drawing interfaces. It may demonstrate how users can create

Behind the MiMo API Price Reduction: The deepest price cut, up to 99%, is for Input (Cache Hit). The core reason is our inference framework now supports hierarchical KV cache optimization for SWA. Pro

Completely agree, @hwchase17 ! This is the meta-level breakthrough we've all been waiting for. Self-optimizing loops finally feel production-ready because LangSmith Engine turns evaluation from a manu

A post about Pope Leo XIV's encyclical on AI. Why the Pope is right, but perhaps not right enough. Artificial intelligence is reshaping the world in front of our eyes: how we communicate, how we acces

Every 'self-evolving agent' paper this year has mutated text: prompts, skill files, workflow graphs, memory schemas. MOSS from USTC & HKUST argues this is the wrong layer. The thing that actually brea

fun read on real tradeoffs & design decisions we debated when designing Engine for the data scale that customers produce one common thread is that we’re pretty strong supporters of just giving the age

One trend that I think you might start to see at big companies is insourcing via hiring: why pay so many outside vendors (legal, marketing, software vendors) when you can hire in-house and harness AI

GLM-5.1 from @Zai_org is now live on OrcaRouter • #1 open-source model on SWE-Bench Pro • Beats closed source models on real-world repo repair benchmarks • MIT licensed • 200K context • Built for long

The best feature of @xai Grok Build right now is how it handles subagents and personas. Most people still treat the model like one very smart intern that has to do everything at once. Grok Build took

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

The most revealing thing about this AI leadership paper is that it reads less like a vision for innovation and more like a glossy whitepaper for a 21st century East India Company. Every generation of

Interesting position paper on agentic AI as a foreseeable pathway to AGI. (bookmark it) There has been strong debate on whether a larger single model get us there or a multi-agent system. The authors

What we find most useful about TST is the decoupling. The training-time efficiency is fully separated from the inference-time architecture, which makes TST a clean addition on top of other pretraining

A startup wants to pull magnesium from seawater without torching the environment. Another wants to take small language models to the podium for enterprise customers. Today @jason and @alex sat down wi

$NBIS announced a partnership with LangChain to integrate Nebius Token Factory with LangChain’s Deep Agents. The goal is to make it easier for teams building AI agents on LangChain to run those worklo

Docs from @NousResearch on how to set up Pareto Code in Hermes: https://hermes-agent.nousresearch.com/docs/user-guide/configuration#openrouter-routing--pareto-code-for-auxiliary-tasks Introducing Pare

Nous Research announced or shared information about their Hermes Agent project via OpenRouter, likely detailing capabilities, updates, or technical specifications for their AI agent system. OpenRouter

The human brain🧠 is incredibly efficient because it only activates the specific neurons needed for a thought. Modern LLMs naturally try to do this too (> 95% of neurons in feedforward layers stay sile

fleet is built on top of deepagents, a model agnostic base harness! try building multi-model agents in fleet today, or build your own deep agent with the underlying sdk! Not every step in an agent wor

NEW paper from Sakana AI (ICLR 2026). A 7B Conductor model just hit SOTA on GPQA-Diamond and LiveCodeBench by orchestrating other LLMs instead of solving problems itself. (great paper! bookmark it!) T