36,952 results for end · 2.742s

News for “end”
17 results • 2735 ms server time
Moozonian News
bing.com• Aug 13, 2026• 1 min read
Alzheimer's patients 'not changing brain health behaviours'The team at the Mass General Brigham Neuroscience Institute found that fewer than 3% of 267 people with Alzheimer's assessed in their study were following recommendations like exercising, getting ...
Moozonian News
github.com• Aug 13, 2026• 1 min read
Show HN: Nanosamur.ai – open-source private speech AI platformnanosamur.ai is an open-source speech AI platform for organizations that cannot send sensitive conversations to a third party.It lets you capture, transcribe, refine, and process speech entirely inside infrastructure you control.Last couple of years I have been consulting for some organizations that work with sensitive data and have to keep them in air gapped environments and based on those experiences I built and open-sourced nanosamur.aiI wanted a speech-to-text stack that could run completely inside customer-controlled infrastructure, and that would not be just a local app you install to transcribe your conf. calls - but an enterprise grade platform that would be model agnostic, could scale and would have multitenancy, observability, webhooks & workflows etc. (basically all the stuff you as an enterprise architect would expect from a solution like this).The easiest place to start is the main repo: https://github.com/nanosamurai/nanosamuraiIt is a docker compose starter setup, there
Advertisement
Moozonian News
github.com• Aug 13, 2026• 1 min read
Show HN: Unicasso – image to ASCII art via optimization with CLIPHi HN!This is a repo to convert images into ASCII and ANSI art.The general technical approach is to use CLIP as a judge on the ASCII art (akin to CLIPasso, for those familiar), while trying to make the glyph space differentiable in a sensible way.I've tested it on macOS and Linux/CUDA. A render takes about an hour and 8 Gb of memory, there's a fast preview mode if you want to watch the optimization process make progress.Paper writeup is in progress -- any feedback would be welcome :)
Moozonian News
news.ycombinator.com• Aug 13, 2026• 1 min read
Ask HN: What browser do you use?At work, I use Chrome mainly because I work on an observability and analytics product, so it makes sense to use the browser that sends everything, everywhere by default.Outside of work, though, I use Zen and have also been thinking about switching to Mullvad. Privacy-focused browsers, or even simple extensions like Mullvad, Zen, Brave, LibreWolf, or Firefox with uBlock Origin are easy to install and use these days, so I'm wondering why so many people still stick with Chrome, Safari, or Edge.What keeps you using your current browser?
Moozonian News
substructure.ai• Aug 13, 2026• 1 min read
Show HN: An agent engine with no SDK, just TOML and webhooksI was looking for a way to add AI agents to multiple systems that I maintain.I had a few requirements:- I work in multiple programming languages, so it needs to work for all of them.- I can control how tools access my system.- I can override the agent loop to try different patterns.- I can iterate on the loop without handling durability, streaming, and the rest of the nitty gritty.- I can iterate locally before deploying.- I can self host.Nothing existed that worked across programming languages, so I built it.It's not an SDK. It's a server that handles durability, streaming, MCP connections, LLM calls and connecting to channels like Slack.You can override every single step of the agent loop by handling a webhook.But you don't have to override anything, you don't even need to handle the webhook. You can define the agent in a TOML file and chat with your agent via Slack in minutes.Point it at your backend to receive a webhook at every decision point. The engine sends the current step and
Moozonian News
news.ycombinator.com• Aug 13, 2026• 1 min read
Ask HN: Small team devs – how do you collab with UI/UX designers in the AI era?Running a 2 person product company, my cofounder (product designer by trade) and I are struggling to get the design/dev process right as AI transforms the way we ship.There are a couple of interrelated problems:1. As we move faster and a higher proportion of our frontend code is AI generated it means more minor UI bugs and inconsistencies. These are generally things that could be zero-shotted by an agent but from what I've found the agentic coding tools for existing mid-sized codebases tend to be developer-focused and not easy for a designer to setup/use.2. Everything was originally designed in Figma but pixel pushing every screen is feeling increasingly redundant. So ideally we'd just rely on some core components built in Figma and then vibe code their implementation. But of course when we want to change an existing component, I tend to just implement that change in code, get design-approval, and ship it: figma never gets updated, so its been pretty much discarded and the actual compo
Moozonian News
news.ycombinator.com• Aug 13, 2026• 1 min read
Show HN: ProbeDeck an iOS app for ClickHouse incident triageAs a backend developer dealing with heavy applications, I run a ClickHouse node with 3.42 TB compressed and 19.10 TB uncompressed amongst its active components. I built ProbeDeck to run some operations on a cluster, inspect a cluster, and read some system logs on my iPhone or iPad with no laptop.The application presents some system tables as screens for running a query, replica state, storage pressure, and mutations. It pulls some stats from the system.metric_log table and shows 0 when that table is not active. One can inspect the system and decide if they want to execute KILL QUERY or KILL MUTATION. Those screens have a confirmation screen. While working with destructive SQL in the editor, a confirmation is needed and is type-safe.The app sends ClickHouse requests via HTTP or HTTPS to the ClickHouse server, or via one SSH bastion if a single SSH hop is needed. ProbeDeck does not proxy requests for a database. It stores passwords, SSH private keys, TLS client certificates, and the secr
Advertisement
Moozonian News
ichabod.dev• Aug 13, 2026• 1 min read
Show HN: Ichabod – The (slightly spooky) headless professional networkHi there HN;Wanted to share a side project I've been playing with this summer.It's a headless professional network, designed to be primarily operated by agents via MCP.I got a frustrated with the hoops I was having to jump through to find teammates who knew their way around agentic workflows, and built something in anger (wow, highly recommend). I just wanted job seekers and companies to have low friction surface areas for their agents to run wild in finding each other.Figuring out how to deal with the agentic volume with marketplace mechanics and guardrails was a fun exercise, so wanted to share what I figured out here.Everything works (so far) but while it's in early access there's spooky sample data in there. If you want to try it, everything's free. Usernames are first come ;)Would love to hear what you think.
Moozonian News
diffusion.alexvd.dev• Aug 13, 2026• 1 min read
Show HN: Diffusion PDF – A Diffusion Image Model Embedded Entirely in a PDF FileHey Hacker News! I'm Alex, I'm 19 and I work at Hack Club!The last two weeks i've been messing around with pdfs. I made slop pdf (https://slop.alexvd.dev -- notice the similar website design), a pdf that generates random ai slop stories when you open it, and I was showing that off to one of my friends who suggested I get the LLM to actually work inside the pdf, without an API call to a relay.I laughed at the idea, but then we did some research together, and we managed to find EvanZhouDev's llm.pdf (https://github.com/EvanZhouDev/llm.pdf). Because it existed, I didn't want to waste my time or my tokens building something like it. So I pivoted, eventually deciding to make a diffusion image model work fully inside a pdf.I forked EvanZhouDev's llm.pdf repo, and eventually managed to get it working (with the help of claude). Here's the finished version.It took a while to train, but was worth it so i can show it to my future classmates (I'm an incoming freshman in college this year).