tools

The Ettin Reranker Family represents a new suite of reranking models released on Hugging Face designed to improve retrieval-augmented generation (RAG) systems by reordering search results based on rel

Context compression isn't new in RAG. Our contribution is making it query-aware, citation-preserving, and fast enough for orchestration. Read the full research blog: https://research.perplexity.ai/art

one of the most memorable cooking pods we've had - both in terms of the content and the food! high protein percentage in both. In this episode, @EngramLab co-founder and CEO @dan_biderman joins @allen

Fine-tune your own embedding model for the price of a coffee. A great reranker can't surface a doc that was never retrieved. A RAG pipeline cannot cite a case it failed to retrieve. See how contrastiv

Jörg Schad is the VP of Engineering at @pinecone. He joins @kbal11 to discuss moving beyond RAG with precomputed context, context artifacts, semantic layers, and AI retrieval. @joerg_schad https://sof

ROSE is the model engine. It reuses the same kernels for LLMs and embeddings. For embeddings, it skips the KV cache and uses ragged attention instead of paged attention. ROSE supports multiple attenti

Every answer in Perplexity starts with embedding and ranking models picking the most relevant results for the query. Today we published research on how we built SoTA serving infrastructure behind thos

Perplexity AI released a preview of its embedding model “pplx‑embed‑v2‑context‑9b” on Hugging Face on September 30, 2026 (7:07 PM local time). The Hugging Face repository page displays 3 122 views and

OpenAI says AI can automate 80% of GDP. Today, with current models. So why hasn't it been automated yet? @swyx says the constraint is supply. Supply of chips and memory. Demand shot through the roof b

Jev and the System One Model: RLCD, intelligence/, reliable AI, & the end of chat-first AI https://www.latent.space/p/jev @typesafeai CEO @CompleteSkeptic explains why AI can solve extraordinarily har

The more time I spend working with coding agents, the more convinced I am that they make software engineering even harder. We can do amazing things with them, but unlocking their full potential requir

I tested Jev and five LLM judges across ten Arize Phoenix evaluators to measure how often their answers changed alongside accuracy, cost, and latency. The post What Jev’s probabilities reveal that rep

Together is #1 on @OpenRouter token share across top open coding models, today: 🥇 @Zai_org GLM 5.3 Flash: 29.2% 🥇 @deepseek_ai V4.1 Flash: 25.6% 🥇 @Kimi_Moonshot Kimi K3: 18.9% Running coding agents o

So dots are either your amplifier or your additional team member, although right now you can have one dot - why? Because otherwise things will get really messy in this new human-AI multiplayer game. T

I'm at OpenAI DevDay today, in Fort Mason, San Francisco. Same as last year I'll be live blogging the keynote and some other notes during the day. OpenAI gave me a free ticket and a seat in the 'creat

Anthropic detailed the activity of its A.I. agents in a blog post on Friday, without naming the targeted websites. But two sources with knowledge of the incidents said Anthropic’s A.I. agents had subm

All week we’re spotlighting teams training past the frontier on Fireworks. @Figma’s AI team is shipping features that change how millions of people design, and with the Training API they can iterate f

A noisy code reviewer gets ignored. Flag too many non-issues and engineers tune it out. @Macroscope got the control they needed with the Fireworks Training API to train a model using their own advanta

GLM-5.3 is now available for training on Fireworks Dedicated Training API and Managed Training surfaces. Built for complex coding and long-horizon agents and now available to train on our dedicated in

together fine-tuning now supports glm-5.3, kimi k2.7-code + more we also added live run metrics, experiment comparisons, early stopping, dataset previews + finer training controls prices are down 30–7

Together Fine-Tuning adds the latest open-weight models, live experiment tracking, Expert LoRA, early stopping, tokenized dataset previews, pre-flight validation, and lower training prices on selected

Deel handles compliance, payroll, and HR questions across 150+ countries. Instead of searching for the answer through an external LLM each time, they fine-tuned small models built on Deel's own compli

TypeSafe’s Jev classifies, scores, and routes without generating text — up to hundreds of times cheaper than an LLM judge. What that changes for evals, confidence routing, and application architecture

Want to RL-train a model on your own task without building the infra? Use our new cookbook with @hud_evals: → Define your task + grader in HUD → Sample + train the model on Fireworks Define the task o

xAI's Grok audio models are now accessible through the Vercel AI Gateway, expanding the platform's capabilities for developers to integrate advanced audio processing into their applications. This inte

This post discusses how the metaphor of 'factories' for AI systems presents a pessimistic framing of the future, arguing that the language and analogies we use to describe AI development shape our per

Together AI announced a Series C funding round and shared details about their company vision, current capabilities, and future direction in open-source AI development and inference optimization. The a

The best base model for training isn't about someone else's benchmarks. Excited to offer @thinkymachines' first open-weights model: Inkling. 975B MoE, multimodal, with Apache 2.0. A great foundation f

The Together AI platform’s dedicated inference architecture consists of three immutable entities: **configs** (engine, GPU type/count, parallelism and optimization profile), **deployments** (a specifi

Inkling-Small is now live on Together AI. @thinkymachines’ new open-weight multimodal model delivers similar performance to Inkling at one-quarter the size, built for coding, agents, and general multi

FLUX 3 is now live on Together AI. @bfl_ai’s new multimodal model generates video and synchronized audio together, with up to 20-second clips, multiple shots, and control from text, images, or keyfram

Radical Numerics, led by CEO Eric Nguyen, is deploying “biological chain‑of‑thought” and multimodal perception techniques to stay ahead of the evolving bio‑defense arms race, enabling rapid design of

Cursor has introduced an auto-review mode feature that enables AI agents to execute tool calls with reduced approval requirements while maintaining safer execution practices. This feature streamlines

Lukas Petersson and Axel Backlund of Andon Labs discuss their work on evaluation methods and benchmarking for AI systems, likely covering approaches to assessing AI capabilities and safety in real-wor

Vercel introduced budget management features for API keys on its AI Gateway, allowing developers to set spending limits and monitor costs for API key usage. This feature helps prevent unexpected charg

Nebius AI announced the Agents Blueprint, a framework integrating multiple tools including LangChain Deep Agents, Tavily AI, Pinecone for vector storage, and Guardrails for building AI agents. This bl

This episode likely discusses red-teaming methodologies and adversarial testing approaches in AI systems, featuring security researchers Zico Kolter and Matt Fredrikson from Carnegie Mellon University

I was at the first AI Engineer Summit @aiDotEngineer ~500 people, limited admission, felt like a secret. Next week it takes over Moscone West: thousands of engineers, 400+ sessions. Huge props to @swy

Agree is a TypeScript library by Boris Cherny that provides a schema validation and serialization system, enabling developers to define data schemas with type safety and validate data at runtime. The

This post discusses ongoing efforts to improve AI safety safeguards, specifically refining systems to accurately differentiate between genuine misuse and legitimate user requests while addressing edge