Knowledge catalogue
LangSmith Engine is how we’re spinning the always-on, self-improvement loop for every agent - Tracing is on for every single agent - Purpose built infra with SmithDB to handle data at agent scale (mor
Recently @pinecone introduced Nexus – a new knowledge-engine layer for AI agents that reduces token use by up to 90%. It’s built on top of a vector database, but shifts reasoning earlier in the pipeli
The post argues that 'return on inference' (ROI) has become the primary metric for evaluating AI investments and business value over the next 18 months, shifting focus from traditional return on inves
UPDATE: Grok has now surpassed 126 million posts on X. The growth is happening incredibly fast with millions of users interacting with Grok directly inside the platform every day. What started as an A
ChatGPT for personal finance is interesting, but you need to know what questions to ask and have enough experience to fact-check assumptions. It really needs to ship with some pre-built skills to help
Gemma-4-31B-it-Pearl supports 32K context, configurable thinking, function calling, and JSON mode. This is Together AI’s first Pearl-powered endpoint. Eventually, we plan to expand our Pearl powered p
Grok Build has three commands for managing memory across sessions: /memory, /flush, and /dream. They're experimental but worth looking at if you've ever been frustrated with how agents forget everythi
40 Grok Build agents tearing through C code in parallel. All supervised by DAD. DAD is a lightweight autonomous tmux supervisor for long-running Grok tasks. Built entirely in Grok Build. /dad 'your ob
arXiv:2605.15051v1 Announce Type: new Abstract: Speculative decoding (SD) accelerates large language model (LLM) inference by using a smaller draft model to propose multiple tokens that are verified b
Contact center AI transformation is accelerating in financial services as new innovations close the gap between surface-level metrics and genuine customer understanding in high-stakes interactions. Fo
arXiv:2605.13910v1 Announce Type: cross Abstract: We present a covariance-aware sampler that improves the quality of pixel-space Diffusion Model (DM) sampling in the few-step regime. We hypothesize th
Dataiku Inc. today announced a deeper integration with Snowflake Inc. aimed at simplifying the creation of enterprise AI agents while preserving governance and operational controls, a growing concern
arXiv:2605.14488v1 Announce Type: new Abstract: Large Language Models (LLMs) augmented with Retrieval-Augmented Generation (RAG) techniques are revolutionizing applications across multiple domains, su
arXiv:2605.14258v1 Announce Type: cross Abstract: Large language models are remarkably capable, yet how computation propagates through their layers remains poorly understood. A growing line of work tr
arXiv:2605.14249v1 Announce Type: new Abstract: We present EnergyLens, an end-to-end framework for energy-aware large language model (LLM) inference optimization. As LLMs scale, predicting and reducin
arXiv:2506.04499v2 Announce Type: replace Abstract: Existing LiDAR 3D object detection methods predominantely rely on sparse convolutions and/or transformers, which can be challenging to run on resour
arXiv:2605.14525v1 Announce Type: new Abstract: In multi-view 3D human pose estimation, models typically rely on images captured simultaneously from different camera views to predict a pose at a speci
arXiv:2605.14218v1 Announce Type: new Abstract: The key problem facing ChatGPT-like AI's use across society is that its behavior can shift, unnoticed, from desirable to undesirable -- encouraging self
arXiv:2605.13874v1 Announce Type: cross Abstract: Autonomous research agents can already run machine learning experiments without human supervision, but many rely on a narrow search strategy: they rep
Gemma-4-31B-it-Pearl supports 256K context, configurable thinking, function calling, and JSON mode. This is Together AI’s first Pearl-powered endpoint. Eventually, we plan to expand our Pearl powered
Gemma-4-31B-it-Pearl supports text and image input, 256K context, configurable thinking, function calling, and JSON mode. This is Together AI’s first Pearl-powered endpoint. Eventually, we plan to exp
arXiv:2602.19533v2 Announce Type: replace-cross Abstract: This paper investigates the grokking phenomenon, which refers to the sudden transition from a long memorization to generalization observed dur
This OpenAI Academy resource explores practical applications of Codex, their AI code generation model, within data science workflows and teams. It likely covers how data scientists leverage Codex to a
This resource from OpenAI's Academy demonstrates practical applications of Codex, their code-generation AI model, within sales team workflows. It likely covers how sales professionals can leverage Cod
arXiv:2605.14455v1 Announce Type: new Abstract: The Intelligence Impact Quotient (IIQ) is a composite metric intended to quantify the depth to which AI systems are integrated into organizational work
arXiv:2601.21349v2 Announce Type: replace-cross Abstract: Mixture-of-Experts (MoE) models scale neural networks by conditionally activating a small subset of experts, where the router plays a central
Les vrais génies de l'histoire. 108 milliards d'humains ont vécu sur Terre. La liste ci-dessous en contient ~100. Soit environ 1 sur 1 milliard. C'est ça, le « autre chose » que les gens cherchent qua
arXiv:2605.13857v1 Announce Type: cross Abstract: The creation of cinematic-quality animal effects necessitates the precise modeling of muscle and fur dynamics, a process that remains both labor-inten
arXiv:2509.22151v3 Announce Type: replace Abstract: Material node graphs are programs that generate the 2D channels of procedural materials, including geometry such as roughness and displacement maps,
This article from Greek City Times critiques casting decisions in Christopher Nolan's adaptation of Homer's Odyssey, arguing that excluding Greek actors undermines the stated goal of diversity in the
arXiv:2605.15040v1 Announce Type: new Abstract: Agentic modeling aims to transform LLMs into autonomous agents capable of solving complex tasks through planning, reasoning, tool use, and multi-turn in
arXiv:2507.21433v3 Announce Type: replace-cross Abstract: Large Reasoning Models (LRMs) are becoming integral to many AI inference systems, enhancing their capabilities with advanced reasoning. Howeve
Telco cloud modernization has become an urgent operational imperative for operators burdened by decades of siloed infrastructure and the demands of 5G, 6G and edge AI. A unified platform approach is n
Multiple observational studies have found that routine adult vaccines are associated with a reduced dementia risk, with some showing risk reductions of 25% to 40%. Researchers hypothesize that certain
arXiv:2605.14982v1 Announce Type: cross Abstract: We address the discounted reward setting in reinforcement learning (RL). To mitigate the value approximation challenges in policy gradient methods, ac
arXiv:2601.16981v2 Announce Type: replace Abstract: We present SyncLight, a method to enable consistent, parametric control over light sources across multiple uncalibrated views of a static scene cond
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
arXiv:2605.14594v1 Announce Type: new Abstract: High-fidelity 3D head generation plays a crucial role in the film, animation and video game industries. In industrial pipelines, studios typically enfor
arXiv:2605.14705v1 Announce Type: new Abstract: Sign language is the primary language for many Deaf and Hard-of-Hearing (DHH) signers, yet most conversational AI systems still mediate interaction thro
arXiv:2605.14972v1 Announce Type: cross Abstract: A fundamental limitation of Text-to-Code is that no guarantee can be obtained about the correctness of the generated code. Therefore, to ensure its co
arXiv:2605.14290v1 Announce Type: cross Abstract: ReAct has become the default architecture across LLM agents, and many existing web agents follow this paradigm. We argue that it is the wrong default
arXiv:2605.14257v1 Announce Type: new Abstract: We describe two types of models for vocabulary difficulty prediction: a high-accuracy black-box model, which achieved the top shared task result in the
arXiv:2605.14478v1 Announce Type: cross Abstract: Context: Retrieval-augmented code generation relies on cross-file repository context, but retrieved snippets may come from obsolete project states. Ob
Cognition AI reports that Devin, their AI coding assistant, enabled AngelList to complete a data migration 5.2 times faster than their original project timeline. The case study highlights Devin's effe
arXiv:2604.03551v2 Announce Type: replace-cross Abstract: Software Engineering 3.0 marks a paradigm shift in software development, in which AI coding agents are no longer just assistive tools but acti
Portable Reachy Mini is likely a compact, mobile robotic arm or manipulation device, with this post from Hugging Face's CEO Clem Delangue presumably announcing or promoting its availability or readine
beautiful tech stack writeup, one of the best i've ever seen in my career. I always advocate that devtools companies write these up, because it fulfils multiple purposes: - tell users the care that go
arXiv:2605.13642v1 Announce Type: cross Abstract: Most anomaly detection systems output scores rather than calibrated decisions, leaving practitioners to choose thresholds heuristically and without cl
arXiv:2605.12809v1 Announce Type: cross Abstract: A critical step for reliable large language models (LLMs) use in healthcare is to attribute predictions to their training data, akin to a medical case
Release: datasette-ip-rate-limit 0.1a0 The datasette.io site was being hammered by poorly-behaved crawlers, so I had Codex (GPT-5.5 xhigh) build a configurable rate limiting plugin to block IPs that w
arXiv:2502.20427v3 Announce Type: replace-cross Abstract: Deepfakes - manipulated or forged audio and video media - pose significant security risks to individuals, organizations, and society at large.
arXiv:2603.20521v2 Announce Type: replace-cross Abstract: Distributed reinforcement learning trains on data from stale, buggy, or mismatched actors, producing actions with high surprisal (negative log
arXiv:2605.13287v1 Announce Type: cross Abstract: Most exploration algorithms search broadly until uncertainty is resolved. When the action space is too large to resolve within budget, practitioners d
Early beta and we are looking forward to your feedback! We will keep improving until Grok Build is absolutely the best in the world An early beta of Grok Build, an agentic CLI for coding, building app
arXiv:2502.05157v3 Announce Type: replace Abstract: The perspective of developing trustworthy AI for critical applications in science and engineering requires machine learning techniques that are capa
Shares of Figma Inc. rose more than 12% in after-hours trading today after the design software company beat earnings and revenue expectations in its fiscal 2026 first quarter and raised its full-year
arXiv:2604.00001v2 Announce Type: replace-cross Abstract: Gradient-based data selection offers a principled framework for estimating sample utility in large language model (LLM) fine-tuning, but exist
arXiv:2605.13352v1 Announce Type: new Abstract: Standard dual-encoder vision-language models that map images and text to deterministic points on a shared unit hypersphere through ell_2 normalization t
arXiv:2605.12823v1 Announce Type: new Abstract: Coarse-grained (CG) molecular dynamics enables simulations of atomic systems such as biomolecules at timescales inaccessible to all-atom (AA) methods, b
arXiv:2605.13706v1 Announce Type: cross Abstract: From pre-training to query-time augmentation, web-scraped data helps to improve the quality and contextual relevancy of content generated by large lan