259 results for text based · 8.704s

uidomains.com
Show HN: Generate domain lists for an LLM to rankhttps://www.uidomains.com/bulk-keyword-csv-exportGood .com's are getting harder and harder to find and existing generator tools are essentially guessing the context based on your search. I created this tool for generating many available domain combinations and one can utilize the CSV export via their own LLM (ChatGPT, Claude etc) to find the best ones. Use the site's built-in generator, word lists, or upload your own. It also support alt domain names too. One search can generate 50,000+ domains that LLMs can scan through and find the best for your use case.
Aug 10, 2026 5:04 PM
github.com
Show HN: Leaves – A text-UI disk usage treemap visualizerhttps://github.com/patonw/leavesGUI disk analyzers are great for figuring out what's filling up your laptop/desktop drive.On containers or remote servers, the options are limited to purely text based utilities (e.g. du) or list-centric TUIs (e.g. ncdu) which are usually limited to viewing one directory at a time.I created leaves to fill that gap.Inspired by classic utilities like WinDirStat and KDirStat, it uses a 2-dimensional treemap^1 visualization to show the entire directory hierarchy with proportionally sized rectangles.It's performant enough to handle millions of files, thanks to Rust and multi-threading. However, block characters aren't as suited as pixels for resolving a large number of items. Leaves can show file-type summaries per directory or partition the top-level directories by extension, allowing you to see not only where space is being used, but also how.For instance, I can see the largest chunk of my home directory is taken up by uv caches for python and old Linux ISOs that I could easily re-downloa
Jul 16, 2026 4:03 PM
news.google.com
Hope Of The States' Sam Herlihy launches captivating new solo single 'Insignificance' via text-based adventure game - NMEhttps://news.google.com/rss/articles/CBMikwFBVV95cUxPVk44cjRRZnUtSUw0blF1ZDg4NmdmdzE3d2FSeHVtZVJ3Yl92dnY1cmlhc3ZuVzFSTjBNeXdYTl9uakV3c284S2thdXpqUkw1R3p1dktvQS0yX25laXR0THhkMmItajVqU1hiTzNFNV9ZQ3VlQTRoMWJMSlF5LWcyT3o2RktVWXY3OVRYRTJCSEQ4TlU?oc=5Hope Of The States' Sam Herlihy launches captivating new solo single 'Insignificance' via text-based adventure game NME
Aug 26, 2026 2:50 PM
seoagent.com
Show HN: See if bloated 'skills' are degrading your coding agent's performancehttps://seoagent.com/skill-graderI read the 'Skills: Attention is all you have' paper from earlier this month and it struck a chord with me. They researched 50k agent skills and found that a ton of them have all these instructions to try to force invocation, as a result of which they all compete for attention and degrade the performance and usefulness.It's kind of a tragedy of the commons situation because if you develop a skill, of course you want to tell the agent to "BE SURE TO INVOKE THIS WHEN USER MENTIONS X" or whatever, but then all the skills add the same language and the agent doesn't know what to do.I built a skill grader to grade Agent skills based on the paper's methodology. Paste Github repo and see score.My own skill got a C, by the way, so I'm improving it by reducing keywords and description bloat, etc.I hope we can get to a place where users all reject the bloated skill trend... it just never made sense intuitively to have thousands of words of context loaded to do simple things.. cough G stack...
Aug 25, 2026 3:15 PM
youtube.com
Show HN: Stage – Build websites together by editing a shared documenthttps://www.youtube.com/watch?v=DfpqJzd8-zkHi everyone,Stage is a collaborative website builder where teams create websites together by editing a shared document.AI website builders today are chat-based, which makes collaboration difficult because the workflow is inherently single-threaded.Stage takes a different approach: 1. Anyone on the team can contribute ideas to a shared document at any time. 2. An AI agent detects the intent behind those changes and updates the website. 3. The website updates live. Because everything happens in one shared document, the full context is preserved and easy to share.We are launching later this week with limited capacity. If you’re interested, please reserve your spot here: https://buildonstage.comCheers!
Aug 25, 2026 9:40 AM
bing.com
YouTube tests prompt-based custom feeds that let you control your homepagehttp://www.bing.com/news/apiclick.aspx?ref=FexRss&aid=&tid=6a8df03b774c4938b523929e27d5f3d3&url=https%3A%2F%2Fwww.dexerto.com%2Fyoutube%2Fyoutube-tests-prompt-based-custom-feeds-that-let-you-control-your-homepage-3402098%2F&c=15766681367743513556&mkt=en-usYouTube is expanding its Custom Feed experiment, giving users more control over their homepage through text prompts.
Aug 25, 2026 7:46 AM
bing.com
Principles of game narrative design, according to a 30-year veteranhttp://www.bing.com/news/apiclick.aspx?ref=FexRss&aid=&tid=6a8d27b56dcc4310bde0bde02ec84be8&url=https%3A%2F%2Fwww.msn.com%2Fen-us%2Fgaming%2Frpg%2Fprinciples-of-game-narrative-design-according-to-a-30-year-veteran%2Far-AA2aQlH1&c=3765541861318592570&mkt=en-usGamers love stories just as much as movies or TV shows. In fact, beloved games share many commonalities with stories that people love. From early classics like text-based adventure games, Myst, and ...
Aug 24, 2026 2:15 PM
news.google.com
Google Research Introduces ME-POIs: A Mobility-Informed Framework that Adds “How a Place Is Used” to Text-Based POI Embeddings - MarkTechPosthttps://news.google.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?oc=5Google Research Introduces ME-POIs: A Mobility-Informed Framework that Adds “How a Place Is Used” to Text-Based POI Embeddings MarkTechPost
Aug 24, 2026 1:56 PM
news.google.com
Walk through a 3D cyberpunk city built purely from ASCII characters — a text-based metropolis runs on a 283KB Rust WebAssembly engine feeding a WebGL renderer - Tom's Hardwarehttps://news.google.com/rss/articles/CBMiwAFBVV95cUxNZldNOF9XTmxtQlBxWWdqX0JQMzEwZ3JtQVNwejE1dXJqR0tZRUJuZTV0aXV1eG9VaUk2LTF6RkVkajl3VE9MbnFRSl9Ka20xd3FQU01lcWk5Z3g4d0Q5aWhPOG5pdC1NV1V6OHNEaG84WXpyOEY4Q2hrVmJFY3gwMXEtRDdfX0R2WDFuMXQ5aTB2UmpFSEhWWWdiZkFBbEpGRWRXa01wS2xyYmJtOWRpNXluOU9SeG1OcUtHYkRBNUo?oc=5Walk through a 3D cyberpunk city built purely from ASCII characters — a text-based metropolis runs on a 283KB Rust WebAssembly engine feeding a WebGL renderer Tom's Hardware
Aug 22, 2026 2:37 PM
news.ycombinator.com
Show HN: Faro – a text message based accountability companionhttps://news.ycombinator.com/item?id=49350828Hey HN! I built justtextfaro.com, a stupidly simple and extremely proactive text message based companion to stop those small tasks from slipping through the cracks. Just text Faro and it will make sure you wont forget it.The problem:The friction. Alarms/Calendars have fussy menus and are cumbersome. You’ll write something in your notes app and never check it again. When you are done with a task you have disable all said alarms/remove calendar events/update your notes app.The solution:Faro is frictionless. 3 key features:1. Get a text every morning of what you have in flight that day2. Alarms/Reminders in any shape you can describe it, no menus. “Nag me until I get my flight tickets to Paris”. “Text me at 2pm next Tuesday to call Bryan back”. “Bug me every few hours to walk the dog”.3. When you are done with a task, just text Faro. No need to edit a note, remove an alarm, or delete a calendar event. Faro will make all changes and deletions necessary.Just text Faro today 1646-879-0459 (t
Aug 18, 2026 6:58 PM
news.ycombinator.com
Trivially bypass text watermarks by requesting a Base64 responsehttps://news.ycombinator.com/item?id=49333167Anthropic plans to release text watermarking based on SynthID, which modulates the PNRG behind the token choosing mechanism deterministically in a way that lets another tool later estimate whether text was written by AI.This is trivial to bypass that, it's current form: 1. Ask for the response/essay/email encoded in base64 2. Decode it using https://www.base64decode.org/While the encoded text will follow the watermarked distribution, the decoded text will not.
Aug 17, 2026 4:01 PM
news.ycombinator.com
Deep-Imager|One-Stop AI Image Generation Platformhttps://news.ycombinator.com/item?id=49296669deep-imager: One-stop AI image platform.Turn text into stunning AI images. Optimize images based on the original, remove backgrounds, watermarks, text, emojis, etc. Explore templates and a gallery of AI art. Register free to create and download. https://deep-imager.com
Aug 14, 2026 10:02 AM
snippety.app
Show HN: Snippety.app – macOS snippet manager I've been building for 6 yearshttps://snippety.appSnippety is my most important project - an advanced, 100% native text expander for Mac and iPhone.I originally started building it for myself, but over time I decided to make it useful for others too. I've really enjoyed working on this app, and in March I quit my job to take some time to rest and focus more on Snippety.Since then, I've added a lot of features, including a compact interface, conditional blocks, a CLI, and more.I've created and maintained this app from top to bottom all by myself :).Snippety is free to try, and I also offer a one-time purchase with lifetime updates. It's probably not the best business model for me, but I really dislike how everything has become subscription-based, so this is my small way of fighting that trend. :)
Aug 13, 2026 8:12 PM
github.com
Show HN: Nanosamur.ai – open-source private speech AI platformhttps://github.com/nanosamurai/nanosamurainanosamur.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
Aug 13, 2026 3:13 PM
github.com
Show HN: Tried some experiments with architecture for Long term memory for LLMhttps://github.com/faisalhussain-devs/MindCache/tree/collapsed_treeThe main ideas that survived the experimentation are:using four memory types — user, knowledge, episodic, and decision memories, each with different lifecycles, different roles and different token budget in the retrieved context. Decision analysis + anchors — decisions can evolve overtime so they can be active or superseded or conditional instead of remaining as unrelated memories. we keep the track of decision memory which is active, superseded or conditional with additional context and using such active decisions related to the query as anchors to further retrieve memories using lexical bm25 often helps. Smart injection — New memories aren't simply assigned to a topic based on similarity. An LLM-guided ingestion step uses the existing topic structure as context to decide where a memory belongs and how it relates to what is already there. This lets the hierarchy grow dynamically instead of becoming a collection of isolated memory nodes.Hierarchical summaries — MindCache adapts the sta
Aug 12, 2026 8:03 PM
github.com
Show HN: Blueferry, iMessage on Linuxhttps://github.com/erikwb/blueferryHey;Blueferry is an app that connects to your iPhone via Bluetooth to expose an iMessage bridge to your Linux desktop. It supports receiving and sending text-based messages, either 1:1 or in group threads. It requires no phone-side software or jailbreak - just Bluetooth pairing.It accomplishes this by using an undocumented? behavior where enabling ANCS via Bluetooth LE (via https://github.com/pzmarzly/ancs4linux 's technique) causes the phone to accept message capability requests over standard Bluetooth. ancs4linux indicate that they've had mixed success with different BT chipsets on the Linux side, though all of the machines I've been able to test it on have been able to negotiate the connection.
Aug 10, 2026 4:35 AM