Normal Science

bytedance/deer-flow

An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of tasks that could take minutes to hours.🦌 DeerFlow - 2.0 English | 中文 | 日本語 | Français | Русский On February 28th, 2026, DeerFlow claimed the 🏆 #1 spot on GitHub Trending following the launch of version 2. Thanks a million to our incredible community — you made this happen! 💪🔥 DeerFlow (Deep Explor...

DeusData/codebase-memory-mcp

High-performance code intelligence MCP server. Indexes codebases into a persistent knowledge graph — average repo in milliseconds. 158 languages, sub-ms queries, 99% fewer tokens. Single static binary, zero dependencies.codebase-memory-mcp The fastest and most efficient code intelligence engine for AI coding agents. Full-indexes an average repository in milliseconds, the Linux kernel (28M LOC, 75K files) in 3 minutes. Answers structural queries in under 1ms. Ships as a single static binary for m...

smicallef/spiderfoot

SpiderFoot automates OSINT for threat intelligence and mapping your attack surface. SpiderFoot is an open source intelligence (OSINT) automation tool. It integrates with just about every data source available and utilises a range of methods for data analysis, making that data easy to navigate. SpiderFoot has an embedded web-server for providing a clean and intuitive web-based interface but can also be used completely via the command-line. It's written in Python 3 and MIT-licensed. FEATURES Web b...

ChinAI #364: Who is Us - the hybridization of innovation and challenges to assessing technological dependence

Greetings from a world where…Star City rocks…As always, the searchable archive of all past issues is here. Please please subscribe here to support ChinAI under a Guardian/Wikipedia-style tipping model (everyone gets the same content but those who can pay support access for all AND compensation for awesome ChinAI contributors).Who is Us: the globalization of innovation and challenges to assessing technological dependenceAll the time, we hear about China's latest benchmarks and indicators to achie...

Import AI 462: Superpersuasion; self-sustaining AI; paths to ASI

Welcome to Import AI, a newsletter about AI research. Import AI runs on arXiv, cappuccinos, and feedback from readers. If you’d like to support this, please subscribe.Subscribe nowAI can decisively out-persuade humans:…“AI systems were reliably more persuasive than expert humans”...Researchers with the University of Oxford, UK AI Security Institute, Stanford University, and the London School of Economics and Political Science, have studied how well AI systems can persuade humans to change their ...

google-research/timesfm

TimesFM (Time Series Foundation Model) is a pretrained time-series foundation model developed by Google Research for time-series forecasting.TimesFM TimesFM (Time Series Foundation Model) is a pretrained time-series foundation model developed by Google Research for time-series forecasting. Paper: A decoder-only foundation model for time-series forecasting, ICML 2024. All checkpoints: TimesFM Hugging Face Collection. Google Research blog. TimesFM in Google 1P Products: BigQuery ML: Enterprise lev...

GLM-5.2: The Most Powerful Open Model yet and the Brutal Reality of Running It

Z.ai’s GLM-5.2 is the new #1 open-weight model — 753B params, MIT license, a 1M-token context and a real architecture trick (IndexShare). But the weights are 1.51TB. What owners and the benchmarks actually say, and the honest hardware reality of running it at home.

n0-computer/iroh

IP addresses break, dial keys instead. Modular networking stack in Rust. less net work for networks Docs Site | Rust Docs What is iroh? Iroh gives you an API for dialing by public key. You say “connect to that phone”, iroh will find & maintain the fastest connection for you, regardless of where it is. Hole-punching The fastest route is a direct connection, so if necessary, iroh tries to hole-punch. Should this fail, it can fall back to an open ecosystem of public relay servers. To ensure these c...

Universal-Debloater-Alliance/universal-android-debloater-next-generation

Cross-platform GUI written in Rust using ADB to debloat non-rooted Android devices. Improve your privacy, the security and battery life of your device.Universal Android Debloater Next Generation Warning DISCLAIMER: Use at your own risk. We're not responsible for anything that could happen to your devices. This is a detached fork of the UAD project. This aims to improve privacy and efficiency (energy, speed, memory) by removing unnecessary and obscure system apps. This can also improve security b...

nautechsystems/nautilus_trader

Production-grade Rust-native trading engine with deterministic event-driven architecture Branch Version Status master nightly develop Platform Rust Python Linux (x86_64) 1.96.0 3.12-3.14 Linux (ARM64) 1.96.0 3.12-3.14 macOS (ARM64) 1.96.0 3.12-3.14 Windows (x86_64) 1.96.0 3.12-3.14 Docs: https://nautilustrader.io/docs/ Website: https://nautilustrader.io Support: support@nautilustrader.io Introduction NautilusTrader is an open-source, production-grade, Rust-native engine for multi-asset, multi-ve...

alexzhang13/rlm

General plug-and-play inference library for Recursive Language Models (RLMs), supporting various sandboxes. Recursive Language Models (RLMs) Full Paper • Blogpost • Documentation • RLM Minimal Overview Recursive Language Models (RLMs) are a task-agnostic inference paradigm for language models (LMs) to handle near-infinite length contexts by enabling the LM to programmatically examine, decompose, and recursively call itself over its input. RLMs replace the canonical llm.completion(prompt, model) ...

Using AI to help physicians diagnose rare genetic diseases affecting children

Researchers used an OpenAI reasoning model to help diagnose rare diseases, identifying 18 new diagnoses in previously unsolved cases.

OpenBMB/VoxCPM

VoxCPM2: Tokenizer-Free TTS for Multilingual Speech Generation, Creative Voice Design, and True-to-Life CloningVoxCPM2: Tokenizer-Free TTS for Multilingual Speech Generation, Creative Voice Design, and True-to-Life Cloning English | 中文 👋 Join our community for discussion and support! Feishu | Discord VoxCPM is a tokenizer-free Text-to-Speech system that directly generates continuous speech representations via an end-to-end diffusion autoregressive architecture, bypassing discrete tokenization t...

swc-project/swc

Rust-based platform for the Web Make the web (development) faster. SWC (stands for Speedy Web Compiler) is a super-fast TypeScript / JavaScript compiler written in Rust. It's a library for Rust and JavaScript at the same time. If you are using SWC from Rust, see rustdoc and for most users, your entry point for using the library will be parser. Also, SWC tries to ensure that If you select the latest version of each crates, it will work for rust users. MSRV of crates is currently 1.73. To update a...

shiyu-coder/Kronos

Kronos: A Foundation Model for the Language of Financial Markets Kronos: A Foundation Model for the Language of Financial Markets Deutsch | Español | Français | 日本語 | 한국어 | Português | Русский | 中文 Kronos is the first open-source foundation model for financial candlesticks (K-lines), trained on data from over 45 global exchanges. 📰 News 🚩 [2025.11.10] Kronos has been accpeted by AAAI 2026. 🚩 [2025.08.17] We have released the scripts for fine-tuning! Check them out to adapt Kronos to your own ...

trycua/cua

Open-source infrastructure for Computer-Use Agents. Sandboxes, SDKs, and benchmarks to train and evaluate AI agents that can control full desktops (macOS, Linux, Windows). Build, benchmark, and deploy agents that use computers Choose Your Path Building your own agent? Start with Cua · Giving a coding agent a computer? Cua Drivers · Evaluating or training models? Cua Bench · Need macOS VMs? Lume Cua Drivers - Background computer-use on macOS and Windows, with Linux pre-release Drive native deskto...

NVIDIA/SkillSpector

Security scanner for AI agent skills. Detect vulnerabilities, malicious patterns, and security risks.SkillSpector Security scanner for AI agent skills. Detect vulnerabilities, malicious patterns, and security risks before installing agent skills. Overview AI agent skills (used by Claude Code, Codex CLI, Gemini CLI, etc.) execute with implicit trust and minimal vetting. Research shows that 26.1% of skills contain vulnerabilities and 5.2% show likely malicious intent. SkillSpector helps you answer...

Introducing LifeSciBench

Introducing LifeSciBench, an expert-authored, expert-reviewed benchmark for evaluating how AI systems handle real-world life science research tasks and decisions.

OpenAI’s o1 correctly diagnosed 67% of ER patients vs. 50-55% by triage doctors

Researchers say results mark a really ‘profound change in technology that will reshape medicine’

Accelerating Gemma 4: faster inference with multi-token prediction drafters

An overview of how Multi-Token Prediction (MTP) drafters are making Gemma 4 models up to 3x faster at inference.

A couple million lines of Haskell: Production engineering at Mercury

What it takes to run 2 million lines of Haskell in production at a fintech company serving 300,000 businesses.

Using “underdrawings” for accurate text and numbers

A technique for accurate text and numbers in AI-generated images: generate the layout deterministically, then ask the image model to paint on top.

ProgramBench: Can language models rebuild programs from scratch?

Abstract page for arXiv paper 2605.03546: ProgramBench: Can Language Models Rebuild Programs From Scratch?

ZAYA1-8B matches DeepSeek-R1 on math with less than 1B active parameters

Who should care If you work with math, science problems, or complex coding tasks and you're looking for something small enough to run locally or cheaply via API, this is worth serious evaluation. The benchmark numbers at 760M active parameters are not normal and the Markovian RSA boost means performance scales with compute budget rather than hitting a fixed ceiling. If you're building agent workflows that need reliable tool calling or multi-step instruction following, look elsewhere fo

Show HN: Apple's SHARP running in the browser via ONNX runtime web

Hi HN, author here. SHARP is Apple's recent single-image 3D Gaussian splatting model (https://arxiv.org/abs/2512.10685). Their reference code is PyTorch + a pretty heavy pipeline; I wanted to see if it could run in a browser with no server hop, so I exported the predictor to ONNX and ran it via onnxruntime-web with the WebGPU EP.What works: drop in an image, get a .ply you can download or preview live, all on your machine — your image never leaves the tab. The model is large (~2.4 GB sidecar) so first load is slow on a cold cache, but inference itself is a few seconds on a recent Mac.Caveats: SHARP's released weights are research-use only (Apple's model license, not the code's). I host the exported ONNX on R2 so thedemo "just works", but you can also export your own from the upstream Apple repo and upload locally.Happy to talk about it in the comments :)

Text-to-CAD

An open source harness for generating CAD models. Contribute to earthtojake/text-to-cad development by creating an account on GitHub.

GLM-5V-Turbo: Toward a Native Foundation Model for Multimodal Agents

Abstract page for arXiv paper 2604.26752: GLM-5V-Turbo: Toward a Native Foundation Model for Multimodal Agents

Learning the Integral of a Diffusion Model

A deep dive on flow maps.

The Road to a Billion-Token Context

Transformers Are Inherently Succinct (2025)

Abstract page for arXiv paper 2510.19315: Transformers are Inherently Succinct

Anthropic/OpenAI may be spending more than $1000 for every $100 you pay them

Coding with LLMs (Claude Code, OpenAI Codex) is often presented as the ‘killer app’ for Generative AI. But looking at data, it seems the one piece of the puzzle missing is actual cost. …

Show HN: Adam – An embeddable cross-platform AI agent library

An embeddable cross-platform AI agent library written in C. Cloud and local LLMs, tool calling, long-term memory, voice, sessions, research mode, self-evolving loops. The SQLite of agent frameworks: small, portable, just works. - sqliteai/adam

Talk Is Cheap: The Operational Impact of LLM Use

What the data says about the operational impacts of LLM use in the software industry

Show HN: I benchmarked LLM agents on fixing real-world security vulnerabilities

I built a benchmark with 20 real CVEs across 18 Python projects (Pillow, GitPython, yt-dlp, urllib3, etc). I've run it over 5 LLM agents (3 OpenAI, 2 poolside) and 3 different prompts (full advisory, locate, diagnose) with a total of 300 runs. The agents are tasked to fix security vulnerabilities in a sandboxed environment and they are scored against a hidden security tests from the maintainer's own fix.Best solve rate was 50%. On the other 50%, some fixes are sometimes coherent and pass all regression tests, but vulnerability still present.The main differentiator I found between models is cost: gpt-5.5 at 12× more expensive than gpt-5.4-mini while producing statistically similar results. Within-family performance gaps are small, which points out the difference is likely due to model training data. I also did a power analysis and the task count needed to detect a meaningful within-family edge at ~700.Full write-up: https://giovannigatti.github.io/cve-benchCode: https://github.com/GiovanniGatti/cve-bench

What Are Tokens in LLMs?

How LLMs split text into tokens, the BPE algorithm, and why

Following the Text Gradient at Scale

RL Throws Away Almost Everything Evaluators Have to Say

How to build a virtual cell and biology scaling laws

Markov Biosciences, a startup in San Francisco, is betting that virtual cells will soon have their GPT moment.

Import AI 461: "Alignment is not on track"; FrontierCode; and synthetic research interns

Welcome to Import AI, a newsletter about AI research. Import AI runs on arXiv, cappuccinos, and feedback from readers. If you’d like to support this, please subscribe.Subscribe nowAI researchers launch new safety startup because “alignment is not on track”:…Sequent will have a portfolio of under-resourced research bets…Researchers from the UK AI Security Institute Alignment team as well as alignment theory startup Timaeus have joined forces to form a new nonprofit research organization, Sequent,...

apple/container

A tool for creating and running Linux containers using lightweight virtual machines on a Mac. It is written in Swift, and optimized for Apple silicon. container container is a tool that you can use to create and run Linux containers as lightweight virtual machines on your Mac. It's written in Swift, and optimized for Apple silicon. The tool consumes and produces OCI-compatible container images, so you can pull and run images from any standard container registry. You can push images that you buil...

LMCache/LMCache

LMCache: Supercharge Your LLM with the Fastest KV Cache Layer A KV Cache Management Layer for Scalable LLM Inference Blog | Documentation | Join Slack | Community Meeting | Roadmap Updates [2026/05] 🔥 Agentic workload benchmark on AMD MI300X (blog). [2026/04] 🔥 LMCache's new multiprocess(MP) architecture release (blog). [2026/03] LMCache at GTC 2026 (post). [2026/01] LMCache multi-node P2P CPU memory sharing, from experimental feature to production (blog). More [2025/11] LMCache x CoreWeave ac...

masterking32/MasterDnsVPN

Advanced DNS tunneling VPN for censorship bypass, optimized beyond DNSTT and SlipStream with low-overhead ARQ, resolver load balancing, high packet-loss stability and speed.# MasterDnsVPN Project 🔐 | نسخه فارسی | English Version | Русская версия | MasterDnsVPN is a scientific and research-oriented project for carrying TCP traffic through DNS queries and responses. In broad goal, it is similar to projects such as DNSTT or SlipStream, but it follows a fundamentally different structure and impleme...

hexo-ai/sia

SIA is a Self Improving AI framework to autonomously improve the performance of any AI system (Model / Agent) on a benchmark task.SIA (Self-Improving AI) Official implementation of SIA: Self Improving AI with Harness & Weight Updates (Hebbar et al., 2026) — a self-improving loop where a language-model agent updates both the harness and the weights of a task-specific agent. The paper reports a 56.6% gain on LawBench, 91.9% runtime reduction on GPU kernels, and 502% improvement on single-cell RNA ...

RyanCodrai/turbovec

A vector index built on TurboQuant, written in Rust with Python bindings A 10 million document corpus takes 31 GB of RAM as float32. turbovec fits it in 4 GB - and searches it faster than FAISS. turbovec is a Rust vector index with Python bindings, built on Google Research's TurboQuant algorithm — a data-oblivious quantizer that matches the Shannon lower bound on distortion, with no codebook training and no separate train phase. Online ingest. Add vectors, they're indexed — no train step, no par...

francescopace/espectre

🛜 ESPectre 👻 - Motion detection system based on Wi-Fi spectre analysis (CSI), with Home Assistant integration. 🛜 ESPectre 👻 Motion detection system based on Wi-Fi spectre analysis (CSI), with native Home Assistant integration via ESPHome. Tip New ML Detector: Neural network-based motion detection. No calibration required, runs on-device. This is an experimental feature, and feedback is welcome in the dedicated ML detector discussion. A snapshot build with the latest changes is also available...

DiffusionGemma: 4x faster text generation

PRC-linked influence operations are targeting AI debates in the US

A new report from OpenAI details PRC-linked influence operations using AI to target U.S. tech debates, data center narratives, tariffs, and false claims about ChatGPT.

ggml-org/llama.cpp

LLM inference in C/C++llama.cpp Manifesto / ggml / ops LLM inference in C/C++ Recent API changes Changelog for libllama API Changelog for llama-server REST API Hot topics Hugging Face cache migration: models downloaded with -hf are now stored in the standard Hugging Face cache directory, enabling sharing with other HF tools. guide : using the new WebUI of llama.cpp guide : running gpt-oss with llama.cpp [FEEDBACK] Better packaging for llama.cpp to support downstream consumers 🤗 Support for the ...

microsoft/pg_durable

PostgreSQL in-database durable execution Website · Docs · Quick Example · GitHub Durable Execution inside PostgreSQL Long-running, fault-tolerant SQL functions for teams that already keep their state in Postgres and want to stop stitching together cron jobs, workers, queues, and status tables to make background work reliable. Define the workflow in SQL, let pg_durable checkpoint each step, and resume after crashes, restarts, or failed steps. Durable execution is now a standard industry pattern, ...

The sample efficiency black hole

One definition of intelligence is sample efficiency - that is to say, how much data do you need to see in a given domain in order to operate fluently and competently. It’s not clear that we’ve actually made much progress on training sample efficiency over the last few years - it seems like more so we’ve dramatically widened and improved the data distribution.The main way that AIs have been getting better is from adding more and better data, and scaling the compute to develop that data in the fir...

Import AI 460: Reward hacking society, RSI data from Anthropic; and RL-based quadcopter racing

Welcome to Import AI, a newsletter about AI research. Import AI runs on arXiv, cappuccinos, and feedback from readers. If you’d like to support this, please subscribe.Subscribe nowSociety can be reward-hacked, just like cyber environments:…Imagine an army of credit card point optimizers gaming the system… forever…Research from Kings College London, Fudan University, and The Alan Turing Institute have built a benchmark, SocioHack, which tests out how well AI systems can learn to ‘beat the system’...