Knowledge catalogue
Loved the keynote talk about this at @aiDotEngineer . As a Age of Empires fan, I might try it -- just for fun :D Don't think I am going to use it for day to day but surely for fun! AgentCraft v1 is li
arXiv:2604.07823v1 Announce Type: new Abstract: Performance, the externalization of intent, emotion, and personality through visual, vocal, and temporal behavior, is what makes a character alive. Lear
arXiv:2509.22750v3 Announce Type: replace Abstract: Real-world multi-hop QA is naturally linked with ambiguity, where a single query can trigger multiple reasoning paths that require independent resol
MiniMax M2.7 is now available on Vercel AI Gateway in two variants: standard and high-speed, accessible without requiring separate provider accounts. It represents a significant improvement over pr...
arXiv:2604.07747v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) can improve low-k reasoning accuracy while narrowing solution coverage on challenging math que
arXiv:2604.06390v1 Announce Type: cross Abstract: Background: Colorectal cancer (CRC) remains a leading cause of cancer-related mortality worldwide. Accurate survival prediction is essential for treat
Now your business analyst in HR, Finance, or Sales team can build a live app or dashboard, a slide deck that updates in real time, or anything for that matter for your CEO. Combine the speed and power
Often discuss my three-level vision for opening GLM to the community: First, we focus on accessibility by lowering the barrier to entry and removing unnecessary constraints so developers can truly exp
AI Engineer Europe 2026 was a three-day technical conference held April 8–10, 2026, at the Queen Elizabeth II Centre in London, marking the AI Engineer series' first flagship European event. It br...
Vercel Sandbox snapshots capture the complete filesystem state of a running sandbox — including installed packages and configured environments — allowing new sandboxes to be launched from that save...
arXiv:2604.08266v1 Announce Type: new Abstract: Leveraging the general world knowledge of Large Language Models (LLMs) holds significant promise for improving the ability of autonomous driving systems
arXiv:2604.08340v1 Announce Type: new Abstract: While Vision-Language Models (VLMs) have achieved remarkable progress in static visual understanding, their deployment in complex 3D embodied environmen
arXiv:2604.06912v1 Announce Type: cross Abstract: MLLMs require high-resolution visual inputs for fine-grained tasks like document understanding and dense scene perception. However, current global res
Alibaba's Qwen 3.6 Plus is now available on Vercel's AI Gateway, accessible via a unified API with no additional provider accounts required. Compared to Qwen 3.5 Plus, this model adds stronger age...
arXiv:2505.24848v4 Announce Type: replace Abstract: To enable egocentric contextual AI in always-on smart glasses, it is crucial to be able to keep a record of the user's interactions with the world,
arXiv:2505.24499v2 Announce Type: replace Abstract: Generating high-quality Scalable Vector Graphics (SVGs) is challenging for Large Language Models (LLMs), as it requires advanced reasoning for struc
The OpenAI Academy 'Research with ChatGPT' tutorial covers how to use ChatGPT's two primary research tools: the Search the Web feature for retrieving live data and sources quickly, and Deep Researc...
arXiv:2604.06802v1 Announce Type: new Abstract: Recent AI systems have achieved gold-medal-level performance on the International Mathematical Olympiad, demonstrating remarkable proficiency at competi
arXiv:2604.08211v1 Announce Type: new Abstract: Modern multimodal generators can now produce scientific figures at near-publishable quality, creating a new challenge for visual forensics and research
arXiv:2604.08501v1 Announce Type: cross Abstract: Science currently offers two options for quality assurance, both inadequate. Journal gatekeeping claims to verify both integrity and contribution, but
arXiv:2506.01062v4 Announce Type: replace Abstract: We introduce SealQA, a new challenge benchmark for evaluating SEarch-Augmented Language models on fact-seeking questions where web search yields con
arXiv:2604.03128v2 Announce Type: replace Abstract: On-policy distillation (OPD) has become a popular training paradigm in the LLM community. This paradigm selects a larger model as the teacher to pro
arXiv:2604.07054v2 Announce Type: replace Abstract: Sales dialogues require multi-turn, goal-directed persuasion under asymmetric incentives, which makes them a challenging setting for large language
arXiv:2604.07737v1 Announce Type: new Abstract: While transformer-based Large Language Models (LLMs) theoretically support massive context windows, they suffer from severe performance degradation when
Since our initial announcement, we have started onboarding beta design partners. - Connect your Lakebase data - Build an application - Deploy to your Databricks account Reach out to your Replit/Databr
arXiv:2604.06523v1 Announce Type: cross Abstract: Quantum operations on pure states can be fully represented by unitary matrices. Variational quantum circuits, also known as quantum neural networks, e
The specific tweet at that URL (status/2042526363899359295) is not publicly accessible via search results, and the content of that exact post could not be retrieved. However, based on closely relat...
arXiv:2604.06765v1 Announce Type: cross Abstract: Recently, multi-Large Language Model (LLM) frameworks have been proposed to solve contextualized tasks. However, these frameworks do not explicitly em
arXiv:2511.03595v2 Announce Type: replace Abstract: High-dimensional reinforcement learning(RL) faces challenges with complex calculations and low sample efficiency in large state-action spaces. Q-lea
The Information wrote that Meta consumes 60.2T tokens per month, or ~750M per employee. Meta is getting absolutely token-mogged by us currently. SemiAnalysis employees consume 1.86B tokens per month.
The AI Engineer conference (@aiDotEngineer) is a community and conference series for software engineers building with AI , organized by swyx (@swyx) and his co-founder Ben. The AI Engineer Code S...
The pace at which useful things are shipping also seems to be accelerating. Model releases are coming faster, of course, but so are significant application and enterprise products (especially from Ant
🚨🇫🇷🇪🇺 This is big: the French government and agencies are officially getting out of Windows & non-EU tech. Each ministry has to present their exit plan before Autumn: collaboration tools, antivirus, A
arXiv:2512.08410v2 Announce Type: replace Abstract: Due to excessive memory overhead, most Multimodal Large Language Models (MLLMs) can only process videos of limited frames. In this paper, we propose
In ChatGPT, a skill is a reusable, shareable workflow — defined by a `SKILL.md` file — that tells ChatGPT how to consistently execute a specific task without starting from scratch each time. Skills...
arXiv:2509.08016v2 Announce Type: replace Abstract: Video Large Language Models (VideoLLMs) face a critical bottleneck: increasing the number of input frames to capture fine-grained temporal detail le
arXiv:2604.07705v1 Announce Type: new Abstract: Aerial vision-and-language navigation (Aerial VLN) aims to enable unmanned aerial vehicles (UAVs) to interpret natural language instructions and autonom
arXiv:2602.22220v2 Announce Type: replace-cross Abstract: Quotation recommendation aims to enrich writing by suggesting quotes that complement a given context, yet existing systems mostly optimize sur
arXiv:2604.06995v1 Announce Type: new Abstract: Existing Graphical User Interface (GUI) reasoning tasks remain challenging, particularly in UI understanding. Current methods typically rely on direct s
arXiv:2604.08281v1 Announce Type: new Abstract: Large reasoning models (LRMs) have achieved strong performance enhancement through scaling test time computation, but due to the inherent limitations of
Yet another illustration of why LLMs aren’t even close to being AGI. The world’s best LLMs are still terrible at poker. We put each model into a 200bb heads-up NLHE match against GTO Wizard AI. The be
After playing with it a bit, Meta's Muse Spark Thinking is fine so far, but really doesn't match the current Big Three models. It also is a bit... weird. Like some strange language & tone, a little lo
Application security posture management company Apiiro Ltd. today announced the launch of a new command-line interface designed to bring application security directly into artificial intelligence-driv
Release: asgi-gzip 0.3 I ran into trouble deploying a new feature using SSE to a production Datasette instance, and it turned out that instance was using datasette-gzip which uses asgi-gzip which was
The *Interconnects.ai* article argues that fears around releasing an open-weight version of Claude Mythos are overstated, noting that closed frontier models still lead open-weight ones in robust, ...
Ryan Lopopolo, a Member of Technical Staff at OpenAI, posted this tweet inviting people to discuss harness engineering with him in-person at Westminster — referencing his broader work on the topic....
CyberAgent, a major Japanese internet and media company, adopted ChatGPT Enterprise and OpenAI's Codex to accelerate engineering and business workflows across its organization. By integrating these...
The AI Engineer World's Fair (AIEWF) held its keynote livestream on YouTube, featuring prominent speakers including Malte Ubl (@cramforce, CTO at Vercel), Raia Hadsell (VP of Research at Google) ,...
The specific tweet at that URL (status ID 2042079804271313343) could not be directly retrieved. However, based on the available context about Ben Golub's recent X/Twitter activity around Refine.ink...
If you want an example of what this looks like in practice, check out the '/research-docs' skill I created for Claude Code https://x.com/jerryjliu0/status/2041564207750246904?s=20 I built a Claude Cod
i'm not gonna lie, this is an emotional moment - when I was coming up in JavaScript, @jsconfeu was incredibly essential to my learning and plugging into the engineering community that became my entire
Replit AI Interviewer is a tool announced by Replit product manager Samuel Spitz, designed to help job seekers prepare for interviews using AI. It is part of a broader series of AI-powered producti...
The specific tweet (status/2042352720489955539) is not publicly accessible or indexed in search results, but one third-party blog did surface the directly relevant detail about the @-mentions impro...
I was unable to retrieve the specific content of the post at the provided URL, as X (formerly Twitter) requires JavaScript and user login to display individual posts, and the specific status ID (20...
Ryan Lopopolo ([@_lopopolo](https://x.com/_lopopolo)), a Member of the Technical Staff on OpenAI's Frontier Product Exploration team, hosted an AMA on Slido in conjunction with his appearance on th...
I'm not able to fetch URLs or browse the internet directly. However, I do have access to a web search tool — let me try searching for this content instead. The specific tweet (status ID 20421847775...
Amazon released the Nova 2 model family on December 2, 2025 at AWS re:Invent, comprising Nova 2 Lite, Nova 2 Pro (Preview), Nova 2 Omni, and Nova 2 Sonic, all featuring a 1-million-token context wi...
A timeless story of grit, faith and rebellion takes center stage as Samson: A Tyndalston Story joins the GeForce NOW library today. The highly anticipated release from Liquid Swords can now be streame
Tesla V14.3 self-driving review. The point releases will bring polish. V15 will far exceed human levels of safety, even in completely unsupervised and complex situations. 600 miles in with FSD v14.3 a
Tether Operations S.A. de C.V., a company best known for operating and issuing the cryptocurrency of the same name, today announced the release of a fully open-source framework for developers to build