Knowledge catalogue
Google's Gemini is getting a feature called 'notebooks' to help you organize things about certain topics in a single place while using the AI chatbot, the company announced on Wednesday. You can pull
GLM-5.1 is Z.ai's post-training upgrade to GLM-5, now available on Together AI, delivering a 28% coding performance improvement through a refined reinforcement learning pipeline while retaining the...
Great paper on improving memory for AI agents. NEW paper: Memory Intelligence Agent (MIA) MIA boosts GPT-5.4 by up to 9% on LiveVQA. Quick summary: Most memory-augmented agents treat memory as a stati
Google Research introduced two AI agents to streamline academic workflows: **PaperVizAgent**, a visualizer agent for drawing academic figures, and **ScholarPeer**, a reviewer agent that automatica...
NVIDIA has introduced a modular, library-based architecture for Omniverse, exposing core components—RTX rendering, PhysX-based simulation, and data storage pipelines—as standalone, headless-first C...
A crypto/DeFi developer named banteg posted on X (Twitter) observing that Dario Amodei was still at OpenAI in 2019, where he worked under Sam Altman from 2016 to 2020 as VP of Research, playing an...
Cursor's Bugbot now self-improves through learned rules derived from real-time code review signals, such as developer reactions, replies to comments, and feedback from human reviewers. Since launc...
Google's Gemma 4, launched on April 2, 2026, surpassed 10 million downloads within its first week, according to Google CEO Sundar Pichai, pushing the cumulative total for all Gemma models past 500 ...
A beginner-friendly tutorial demonstrating how to build a ~3.2M parameter LLM from scratch using Mary Shelley's *Frankenstein* as the sole training corpus, designed to run on Kaggle's free GPU in u...
`citracer` is a small Python CLI tool available on PyPI that traces citation chains for any keyword across research papers, helping researchers identify where a concept originates in a citation gra...
The specific post (status ID 2041973286087880810) could not be retrieved — it did not appear in search results, and X (Twitter) requires a login to access individual posts directly. The snippet pro...
To anyone who read Rebooting AI back in (checks notes) 2019, this is both hilarious and unsuprising. The field has wasted 7 years on an architecture that can’t solve one of the most basic litmus tests
Replit introduced a **stock analyzer skill** for its AI Agent platform, allowing users to perform stock analysis directly within the Replit environment. Users can activate it by asking the Agent t...
Top Community Contributors: @SHL0MS (7 PRs) — p5js creative coding skill, manim-video skill + 5 reference expansions, research-paper-writing, Nous OAuth fix, manim fix @sidbing (3 PRs) — Firecrawl clo
AI Gateway combines content deletion with provider routing agreements; model exceptions, caching, metadata and application storage limit the ZDR promise.
I was unable to directly access the specific X (Twitter) post or the underlying paper it references, and my general web search did not surface the specific study being discussed. I cannot responsib...
I was unable to retrieve the specific content of the X (Twitter) post at the provided URL or the linked YouTube video (`youtube.com/watch?v=tYhgWRJeYzs`). The tweet ID `2041637736382160925` appears...
GLM-5.1: Towards Long-Horizon Tasks Chinese AI lab Z.ai's latest model is a giant 754B parameter 1.51TB (on Hugging Face) MIT-licensed monster - the same size as their previous GLM-5 release, and shar
User Kevin Kern reported successfully integrating OpenCode into Taugentic (an AI-powered browser/agent environment), enabling use of GLM-5.1 via Z.ai's GLM Coding Plan. GLM-5.1 is Z.ai's next-gener...
A user on X (@willebrew) shared positive impressions of Cognition's SWE-1.6 Fast model, noting that a prototype UI it generated surpassed the output of Figma Make. SWE-1.6 is Cognition's latest mo...
This uses LiteParse, which is great for fast text search: https://developers.llamaindex.ai/liteparse/?utm_medium=social&utm_source=xjl If you're interested in deeper VLM-enabled search, check out Llam
Visually rich documents are especially challenging for agents. Tables, charts, and images often break traditional document pipelines, making complex reasoning difficult📄 So we teamed up with @lancedb