Home

Microsoft BitNet: 100B Param 1-Bit model for local CPUs
redm about 4 hours ago

Microsoft BitNet: 100B Param 1-Bit model for local CPUs

BitNet is an open-source project by Microsoft that aims to provide a scalable and efficient blockchain network for decentralized applications. The project explores novel consensus mechanisms and optimization techniques to address the performance and scalability challenges of traditional blockchain platforms.

github.com
168 91
Summary
AI Agent Hacks McKinsey
mycroft_4221 about 7 hours ago

AI Agent Hacks McKinsey

The article describes how a team of researchers successfully exploited vulnerabilities in McKinsey's AI platform, highlighting the importance of robust security measures for AI systems and the need for thorough testing and validation to prevent such breaches.

codewall.ai
163 60
Summary
TADA: Fast, Reliable Speech Generation Through Text-Acoustic Synchronization
smusamashah about 11 hours ago

TADA: Fast, Reliable Speech Generation Through Text-Acoustic Synchronization

The article discusses the open-source release of TADA, a platform for developing AI-powered conversational agents. TADA provides a flexible and extensible architecture that can be used to build and deploy chatbots, virtual assistants, and other conversational applications.

hume.ai
84 22
Summary
UK MPs give ministers powers to restrict Internet for under 18s
robtherobber about 2 hours ago

UK MPs give ministers powers to restrict Internet for under 18s

The article discusses the UK government's plans to grant ministers the power to restrict access to the entire internet, as part of the Online Safety Bill. This move has raised concerns about censorship and the potential for abuse of these broad powers.

openrightsgroup.org
61 46
Summary
Temporal: The 9-Year Journey to Fix Time in JavaScript
robpalmer about 1 hour ago

Temporal: The 9-Year Journey to Fix Time in JavaScript

The article discusses the Temporal API, a new JavaScript standard that simplifies date and time manipulation. It provides an overview of the Temporal API's features, including its ability to handle time zones, calendars, and various date/time formats.

bloomberg.github.io
55 16
Summary
I'm going to build my own OpenClaw, with blackjack and bun
rcarmo about 9 hours ago

I'm going to build my own OpenClaw, with blackjack and bun

The article describes Piclaw, an open-source Python library that provides a simple and flexible way to manage and manipulate images. Piclaw offers a set of tools for resizing, cropping, and applying various effects to images, making it a useful tool for image processing and automation tasks.

github.com
41 34
Summary
Wiz Joins Google
aldarisbm about 2 hours ago

Wiz Joins Google

Google has completed the acquisition of the cloud security startup Wiz, marking a significant move in the tech giant's efforts to strengthen its cloud security offerings and capabilities.

wiz.io
38 11
Summary
AutoKernel: Autoresearch for GPU Kernels
frozenseven about 9 hours ago

AutoKernel: Autoresearch for GPU Kernels

AutoKernel is an open-source project that aims to automate the process of compiling and optimizing kernel modules for different hardware platforms, making it easier for developers to build and deploy custom kernels.

github.com
37 7
Summary
Making WebAssembly a first-class language on the Web
mikece about 12 hours ago

Making WebAssembly a first-class language on the Web

The article discusses Mozilla's efforts to make WebAssembly a first-class language on the web, by improving its performance, interoperability, and developer experience, with the goal of enabling a more diverse set of applications on the web.

hacks.mozilla.org
33 4
Summary
Where did you think the training data was coming from?
speckx about 3 hours ago

Where did you think the training data was coming from?

The article discusses the origins of the training data used by Meta (Facebook) to develop their AI-powered smart glasses. It examines how Meta acquired and used data from various sources, including social media platforms, to train their computer vision algorithms for the glasses.

idiallo.com
30 3
Summary
Why does AI tell you to use Terminal so much?
ingve about 8 hours ago

Why does AI tell you to use Terminal so much?

The article explores the reasons why artificial intelligence (AI) systems often recommend using the terminal or command line interface, highlighting its advantages in terms of control, flexibility, and efficiency when working with complex tasks or data-intensive applications.

eclecticlight.co
25 36
Summary
Where Some See Strings, She Sees a Space-Time Made of Fractals
tzury about 1 hour ago

Where Some See Strings, She Sees a Space-Time Made of Fractals

The article explores the work of theoretical physicist Natalie Wolchover, who is investigating the possibility that space-time may be made of fractals, rather than strings. Wolchover's unconventional approach to understanding the fundamental nature of reality challenges the traditional string theory framework.

quantamagazine.org
15 0
Summary
As US missiles leave South Korea, the Philippines asks: are we next?
etiam about 6 hours ago

As US missiles leave South Korea, the Philippines asks: are we next?

The article discusses the U.S. withdrawal of missile systems from South Korea, and the Philippines' concerns about potentially becoming the next target for such relocations. It explores the geopolitical implications and regional dynamics surrounding these developments.

scmp.com
14 8
Summary
Show HN: Klaus – OpenClaw on a VM, batteries included
robthompson2018 39 minutes ago

Show HN: Klaus – OpenClaw on a VM, batteries included

We are Bailey and Robbie and we are working on Klaus (https://klausai.com/): hosted OpenClaw that is secure and powerful out of the box.

Running OpenClaw requires setting up a cloud VM or local container (a pain) or giving OpenClaw root access to your machine (insecure). Many basic integrations (eg Slack, Google Workspace) require you to create your own OAuth app.

We make running OpenClaw simple by giving each user their own EC2 instance, preconfigured with keys for OpenRouter, AgentMail, and Orthogonal. And we have OAuth apps to make it easy to integrate with Slack and Google Workspace.

We are both HN readers (Bailey has been on here for ~10 years) and we know OpenClaw has serious security concerns. We do a lot to make our users’ instances more secure: we run on a private subnet, automatically update the OpenClaw version our users run, and because you’re on our VM by default the only keys you leak if you get hacked belong to us. Connecting your email is still a risk. The best defense I know of is Opus 4.6 for resilience to prompt injection. If you have a better solution, we’d love to hear it!

We learned a lot about infrastructure management in the past month. Kimi K2.5 and Mimimax M2.5 are extremely good at hallucinating new ways to break openclaw.json and otherwise wreaking havoc on an EC2 instance. The week after our launch we spent 20+ hours fixing broken machines by hand.

We wrote a ton of best practices on using OpenClaw on AWS Linux into our users’ AGENTS.md, got really good at un-bricking EC2 machines over SSM, added a command-and-control server to every instance to facilitate hotfixes and migrations, and set up a Klaus instance to answer FAQs on discord.

In addition to all of this, we built ClawBert, our AI SRE for hotfixing OpenClaw instances automatically: https://www.youtube.com/watch?v=v65F6VBXqKY. Clawbert is a Claude Code instance that runs whenever a health check fails or the user triggers it in the UI. It can read that user’s entries in our database and execute commands on the user’s instance. We expose a log of Clawbert’s runs to the user.

We know that setting up OpenClaw is easy for most HN readers, but I promise it is not for most people. Klaus has a long way to go, but it’s still very rewarding to see people who’ve never used Claude Code get their first taste of AI agents.

We charge $19/m for a t4g.small, $49/m for a t4g.medium, and $200/m for a t4g.xlarge and priority support. You get $15 in tokens and $20 in Orthogonal credits one-time.

We want to know what you are building on OpenClaw so we can make sure we support it. We are already working with companies like Orthogonal and Openrouter that are building things to make agents more useful, and we’re sure there are more tools out there we don’t know about. If you’ve built something agents want, please let us know. Comments welcome!

klausai.com
12 5
Summary
Show HN: Open-source browser for AI agents
theredsix about 2 hours ago

Show HN: Open-source browser for AI agents

Hi HN, I forked chromium and built agent-browser-protocol (ABP) after noticing that most browser-agent failures aren’t really about the model misunderstanding the page. Instead, the problem is that the model is reasoning from a stale state.

ABP is designed to keep the acting agent synchronized with the browser at every step. After each action (click, type, etc), it freezes JavaScript execution and rendering, then captures the resulting state. It also compiles the notable events that occurred during that action loop, such as navigation, file pickers, permission prompts, alerts, and downloads, and sends that along with a screenshot of the frozen page state back to the agent.

The result is that browser interaction starts to feel more like a multimodal chat loop. The agent takes an action, gets back a fresh visual state and a structured summary of what happened, then decides what to do next from there. That fits much better with how LLMs already work.

A few common browser-use failures ABP helps eliminate: * A modal appears after the last Playwright screenshot and blocks the input the agent was about to use * Dynamic filters cause the page to reflow between steps * An autocomplete dropdown opens and covers the element the agent intended to click * alert() / confirm() interrupts the flow * Downloads are triggered, but the agent has no reliable way to know when they’ve completed

As proof, ABP with opus 4.6 as the driver scores 90.5% on the Online Mind2Web benchmark. I think modern LLMs already understand websites, they just need a better tool to interact with them. Happy to answer questions about the architecture, forking chrome or anything else in the comments below.

Try it out: `claude mcp add browser -- npx -y agent-browser-protocol --mcp` (Codex/OpenCode instructions in the docs)

Demo video: https://www.loom.com/share/387f6349196f417d8b4b16a5452c3369

github.com
11 5
Summary
Ig Nobel award ceremony moving to Zurich due to concern over U.S. travel visas
ilamont about 3 hours ago

Ig Nobel award ceremony moving to Zurich due to concern over U.S. travel visas

The Ig Nobel Prizes, which honor unusual and imaginative scientific achievements, are moving their award ceremony from the United States to Switzerland due to concerns over US travel visas for international attendees.

swissinfo.ch
9 0
Summary
Gemma Needs Help
pr337h4m about 10 hours ago

Gemma Needs Help

The article discusses a hypothetical scenario where an individual named Gemma needs help, and explores the moral and practical considerations involved in providing that assistance. It examines factors such as the degree of personal sacrifice, the likelihood of success, and the potential consequences of action or inaction.

lesswrong.com
7 0
Summary
Show HN: Rewriting Mongosh in Golang Using Claude
debarshri 38 minutes ago

Show HN: Rewriting Mongosh in Golang Using Claude

The article describes go-mongosh, a Go-based driver for the MongoDB database that provides a user-friendly shell interface for interacting with MongoDB instances. The tool aims to simplify MongoDB operations and offers features like auto-completion, history tracking, and support for various MongoDB operations.

github.com
6 1
Summary
Tech Silicon Valley is buzzing about this new idea: AI compute as compensation
cdrnsf about 3 hours ago

Tech Silicon Valley is buzzing about this new idea: AI compute as compensation

The article discusses how the co-founder and CTO of OpenAI, Greg Brockman, believes that AI compute power could eventually be used to compensate software engineers based on their real-time productivity and value-add, rather than traditional salary structures.

businessinsider.com
5 1
Summary
Show HN: Faster, cheaper Claude Code with local semantic code search via sqlite
luckyturkey about 3 hours ago

Show HN: Faster, cheaper Claude Code with local semantic code search via sqlite

This article introduces Ory Lumen, a semantic search engine that uses the Claude language model to provide more relevant and accurate search results. The article explains how Ory Lumen combines natural language processing and machine learning to understand the context and meaning behind user queries, improving the search experience.

ory.com
5 0
Summary