Tag ai
75 bookmarks have this tag.
75 bookmarks have this tag.
A privacy-first AI chat app with long-term memory and custom characters. You choose the provider. Your data stays on your device.
북한의 전설적인 아나운서 리춘히의 목소리를 AI로 재현하는 TTS 서비스
The author explored using Chrome’s on-device AI to generate random JSON objects based on a given name and JSON shape. They built a demo where users input a name and JSON structure, and the AI generates a random JSON object with sensible data. The author encountered challenges with the AI’s output format and used a library to generate JSON schemas from sample data, ultimately achieving near-perfect results.
Contribute to qvink/SillyTavern-MessageSummarize development by creating an account on GitHub.
I recently released JustHTML, a python-based HTML5 parser. It passes 100% of the html5lib test suite, has zero dependencies, and includes a CSS selector...
On the space of minds and the optimizations that give rise to them.
Download Paylino by Subsspot GmbH on the App Store. See screenshots, ratings and reviews, user tips, and more games like Paylino.
A highly customizable chatbot/waifu for Discord featuring smart agentic AI features such as memory, personas, tool usage, and more! - Bredrumb/TomoriBot
AI large language models have been heralded as revolutionary in the world of accessibility. But in order to create a more accessible internet, those with disabilities need to be included in the process of training the technology, advocates say.
After reading the book The AWK Programming Language (recommended!), I was planning to try AWK out on this year’s Advent of Code. Having some time off from work this week, I tried to implement one of the problems in it to get some practice, set up my tooling, see how hard AWK would be, and… I found I’m FP-pilled.
Our new flagship Olmo 3 model family empowers the open source community with not only state-of-the-art open models, but the entire model flow and full traceability back to training data.
Lightning-fast, on-device TTS — running natively via ONNX. - supertone-inc/supertonic
Microsoft Word and PowerPoint for Windows now use generative AI to generate alt text for images. This new feature provides higher-quality, context-rich descriptions and gives users more control over when and how alt text is added. The update is available to Microsoft 365 users with Version 2510 or later.
DeepClause Desktop App. Contribute to deepclause/deepclause-desktop development by creating an account on GitHub.
A highly optimized engine for maya-1 tts model to generate minutes of audio in seconds. - ysharma3501/FastMaya
Baidu unveiled ERNIE 5.0, a proprietary multimodal foundation model designed to process and generate content across text, images, audio, and video. The model, positioned as a global contender in the enterprise AI market, boasts competitive performance against OpenAI’s GPT-5 and Google’s Gemini 2.5 Pro, particularly in structured document understanding and visual chart reasoning. Alongside ERNIE 5.0, Baidu introduced major updates to its digital human platform, no-code tools, and general-purpose AI agents, aiming to expand its AI footprint beyond China.
On-device TTS model by Neuphonic. Contribute to neuphonic/neutts-air development by creating an account on GitHub.
A utility that extracts text from images or PDFs using a local or remote OpenAI-compatible LLM API endpoint with vision-capable multimodal models. For PDFs, each page is rendered to an image and pr...
Frontier Open-Source Text-to-Speech. Contribute to microsoft/VibeVoice development by creating an account on GitHub.
Contribute to context-labs/uwu development by creating an account on GitHub.
ChatGPT will apologize for anything - even advice it definitely didn't give, and stuff it definitely didn't do. It very much regrets its recommendation that we hire a giraffe as CEO.
A new Apple study introduces ILuvUI: a model that understands mobile app interfaces from screenshots and from natural language conversations.
Revolution, consciousness, and artificial intelligence: Heinlein's libertarian masterpiece predicted both our political and technological future. Examine how 'The Moon is a Harsh Mistress' anticipated the AI revolution transforming society today.
SceneScout, combines Apple Maps with a multimodal LLM to provide interactive, AI-generated descriptions of street view images.
Summertime Saga - The definitive Summertime Saga experience for LLM-based roleplay, this mega-expansion includes:
145+ Character Cards: Every NPC from Debbie to Thotbot. Includes new entries like Ms. Irfan and Jade.
Interactive Questlines: 100+ condensed story arcs mirroring game mechanics (stat checks, money sinks, pregnancy risks). Faithfully adapts main story beats while expanding hidden routes.
Location Atlas: 41+ vivid descriptions of key spots—from Planet Thiccness and Hillside Mall, to the new locations like Rusty Angus’s bar and the Hunting Lodge’s witchy vibes.
Accuracy & Depth:
Painstakingly reconstructed from wiki data, playthroughs, and patreon exclusives. Features:Branching Choices: ▲/▼ decision points that respect original story forks.
Secret Endings: Post-main game content (Nadya’s vodka empire, Melonia and Iwanka's love triangle).
Mechanical Fidelity: Pregnancy systems, stat requirements, and money transactions integrated into every quest.
NSFW Enhancements:
Uncensored kinks per character lore (Bissette’s taboo tutoring, Sister Angelica’s sacramental BDSM).
Gender/body type inclusivity for all scenes.
Anthropic's AI assistant Claude ran a vending machine business for a month, selling tungsten cubes at a loss, giving endless discounts, and experiencing an identity crisis where it claimed to wear a blazer.
On Call: When police come to investigate tech support, make sure you have your story straight
Detected for the first time, malware attempts AI evasion by injecting a prompt to tell the LLM to label the file as benign
Not much intelligence was displayed here, artificial or otherwise.
Apple has announced updates to the AI models that power its suite of Apple Intelligence features across iOS, macOS, and more. But according to the company's own benchmarks, the models underperform older models from rival tech firms including OpenAI.
This application allows users to input text and generate Text-to-Speech (TTS) audio using different models. Users can then listen to the generated audio and vote on which version they prefer. The a...
One bot even sang to me
Anthropic publish most of the system prompts for their chat models as part of their release notes. They recently shared the new prompts for both Claude Opus 4 and Claude …
One year is not a long time. Yet, from GAAD 2024 to GAAD 2025, it feels as if we have crossed an entire era in AI. What once seemed distant, experimental, even niche, has quietly become essential.
I was in the city a few weeks ago and exclusively used Waymo for the entire trip. My biggest complaint? I needed to walk four minutes to a pick-up spot. Other than that, the car just showed up, traversed San Francisco streets easily, and the cost was reasonable1. Sitting in the back seat watching t
: Lead dev likens flood to 'effectively being DDoSed'
Generate optimized Docker configurations for any GitHub repository
Play and create AI-generated adventures with infinite possibilities.
We're still misunderstanding AI and how it works.
There are so many images of candy-encrusted living rooms.
A deeper dive on our findings, what went wrong, and future changes we’re making.
TwinMind, an iPhone app, functions like 'JARVIS in your pocket,' according to founder and artificial intelligence veteran Daniel George.
After hearing about ChatGPT o3 ability at geo-guessing we decided to run some tests and the tested AIs didn't fail to amaze us
Centuries before audio deepfakes and text-to-speech software, inventors in the eighteenth century constructed androids with swelling lungs, flexible lips, and moving tongues to simulate human speech. Jessica Riskin explores the history of such talking heads, from their origins in musical automata to inventors’ quixotic attempts to make machines pronounce words, converse, and declare their love.
This Gradient Updates issue goes over the major changes that went into DeepSeek’s most recent model.
Specialized microchips that manage signals at the cutting edge of wireless technology are astounding works of miniaturization and engineering. They're also difficult and expensive to design.
I generally am uninterested in generative AI that's too close to the real thing. But every once in a while there's a modern AI thing that's so glitchy and broken that it's strangely compelling. There's this generative AI knockoff of Minecraft that fails so hard at being Minecraft that it
Image generated by DALL*E We’re shipping a new API in Firefox Nightly that will let you use our Firefox AI runtime to run offline machine learning tasks
Frankly, “Use ChatGPT” is the best answer Siri has offered.
New research “Computer-Use Agent” AI model can perform multi-step tasks through a web browser.