Not another AI news riverOfficial evidence firstOne event can belong to many entitiesAction required is separate from popularityCommunity discussion never substitutes for fact
Models | Gemini API | Google AI for Developers Skip to main content / English Deutsch Español – América Latina Français Indonesia Italiano Polski Português – Brasil Shqip Tiếng Việt Türkçe Русский עברית العربيّة فارسی हिंदी বাংলা ภาษาไทย 中文 – 简体 中文 – 繁體 日本語 한국어 Get API key Cookbook Community Sign in Docs API reference Gemini API Docs API reference Get API key Cookbook Community Get started Overview Get started API keys Pricing Coding agent setup API CLI Models All models Latest Gemini models Nano Banana Veo Gemini Omni Flash Lyria 3.5 & Lyria Clip Overview Lyria RealTime Lyria prompt guide Text-to-speech Overview Voice design Voice replication Transcribe Live Live translate Embeddings Robotics Overview Spatial reasoning Agentic vision Task orchestration Robotics with streaming Video understanding Core capabilities Text Image Image generation 🍌 Image understanding Video Video overview Video understanding Documents Speech and audio Speech generation Audio understanding Audio transcription Thinking Thinking Thought signatures Structured outputs Function calling Long context Long decode Agents Overview Quickstart Antigravity agent Building managed agents Environments Credentials Hoo
Models | Gemini API | Google AI for Developers Skip to main content / English Deutsch Español – América Latina Français Indonesia Italiano Polski Português – Brasil Shqip Tiếng Việt Türkçe Русский עברית العربيّة فارسی हिंदी বাংলা ภาษาไทย 中文 – 简体 中文 – 繁體 日本語 한국어 Get API key Cookbook Community Sign in Docs API reference Gemini API Docs API reference Get API key Cookbook Community Get started Overview Get started API keys Pricing Coding agent setup Models All models Latest Gemini models Nano Banana Veo Gemini Omni Flash Lyria 3.5 & Lyria Clip Overview Lyria RealTime Lyria prompt guide Text-to-speech Overview Voice design Voice replication Transcribe Live Live translate Embeddings Robotics Overview Spatial reasoning Agentic vision Task orchestration Robotics with streaming Video understanding Core capabilities Text Image Image generation 🍌 Image understanding Video Video overview Video understanding Documents Speech and audio Speech generation Audio understanding Audio transcription Thinking Thinking Thought signatures Structured outputs Function calling Long context Agents Overview Quickstart Antigravity agent Building managed agents Environments Credentials Hooks Deep Research age
Models | Gemini API | Google AI for Developers Skip to main content / English Deutsch Español – América Latina Français Indonesia Italiano Polski Português – Brasil Shqip Tiếng Việt Türkçe Русский עברית العربيّة فارسی हिंदी বাংলা ภาษาไทย 中文 – 简体 中文 – 繁體 日本語 한국어 Get API key Cookbook Community Sign in Docs API reference Gemini API Docs API reference Get API key Cookbook Community Get started Overview Get started API keys Pricing Coding agent setup Models All models Latest Gemini models Nano Banana Veo Gemini Omni Flash Lyria 3.5 & Lyria Clip Overview Lyria RealTime Lyria prompt guide Text-to-speech Transcribe Live Live translate Embeddings Robotics Overview Spatial reasoning Agentic vision Task orchestration Robotics with streaming Video understanding Core capabilities Text Image Image generation 🍌 Image understanding Video Video overview Video understanding Documents Speech and audio Speech generation Audio understanding Audio transcription Thinking Thinking Thought signatures Structured outputs Function calling Long context Agents Overview Quickstart Antigravity agent Building managed agents Environments Credentials Hooks Deep Research agent Tools Overview Google Search Google M
Hello Show HN, I'm a college student, and I enjoy playing word games like Codenames, but it can be hard sometimes to find enough people to play when everyone is available, so I made an app that allows you to fill any seat with an AI teammate and also play against AI. This way it allows for people to get the full strategic experience of codenames just on their own. Through this experiment, I was also able to measure and benchmark a few different LLMs through AWS Bedrock API calls and give them ELO ratings based on stuff like win rate and clue/guess accuracy. If anyone is interested, they can see more about my benchmarking methodology here: https://wordspies.com/hn#method . I think it's pretty interesting because it gives you a lot of insight into these various LLMs' NLP capabilities. A few interesting stats were that I rated Gemini 4 Argon at 1775, GPT-6.1 Sol at 1744, GPT-6 Astra at 1723, Claude Fable 5.1 at 1623, and Claude Opus 5.5 at 1592. You'll find a few interesting things there, like how, although newer, more expensive models tend to perform better, some rare exceptions exist, like Kimi K2.5 slightly edging out Kimi K3. Check out the site if you're interested in NLP and data
I have created few AI images using Claude. The image is perfectly created. But at the bottom there is a watermark image of AI that keeps coming up. I want to remove that watermark. I already tried using ChatGPT, Canva, Adobe, Gemini but still the output doesn't match the original one generated by claude. Anyone knows of any free tools which can be used to do this ? (I don't want to sign up and create an account to access this tool)
Ran into this while swapping external drives between Windows and Mac -- it seems the only reliable way to keep the benefits of NTFS (journaling) and allow writes from MacOS is to use third-party $ commercial drivers. I am not knowledgeble about what makes a driver so I asked (Gemini) -- and I am told this involves a fairly complex low level OS hooks and bypassing OS protections etc with a lot of edge cases -- so today's frontier models are unlikely to produce a reliable driver implementation. I was surprised to hear. If we believe the AI marketing shouldn't this be solved relatively easily?
Will we still be going on websites? Will people continue to install mobile apps? Or are we all going to be living in AI assistant walled gardens, telling it "let's order groceries" or will it just do things for us so we're not ordering things manually? For the broader people (outside of tech, everyone else), what will the next 10-20 years look like? Most people outside of tech circles don't use AI, at least not on purpose. Gemini enhanced search results are about the most they will use, and from those I've talked to, some didn't even know that it was "AI" which is mind-blowing.
When GPT-6/Gemini launched recently, a lot of the 3D demos used blender-mcp ( https://github.com/ahujasid/blender-mcp ). It's cool, but you have to install blender locally and wire up plugins just to try a prompt or share a run. I built a browser-based 3D mesh playground so you can hook up your own coding agent over MCP (or run in-browser) directly in a tab. It runs on three.js + manifold-3d for blender-like boolean/mesh editing in JS, and gives the agent a render_preview tool to take multi-view screenshots (front/right/top/iso + custom camera angles + clay mode). That way the agent can look at what it built and fix the geometry, similar to how it iterates when building a website. The submitted link is a trace of Gemini reconstructing a Copenhagen canal scene from a photo: it hits a script error on the first pass, fixes the bug, and then goes through several rounds of checking 4-view and close-up render_preview screenshots to tweak the geometry.
Hi HN! Fakeipedia is an automatic world-building platform which takes an imagined world and makes a whole wiki that you can endlessly explore by clicking red links. I came up with this idea a few months ago after playing around with worldbuilding in Gemini, but I didn't want to release it until a powerful enough model could do it justice, and I decided that Argon is creative enough to write articles that are worth reading. I was surprised how well it turned out and how engaging some of the writing actually is. If you want to generate an article there is a nominal charge attached ($0.90), which helps cover AI/Stripe costs, and I think I just about break even. You can also steer the generation ala choose-your-own-adventure books when generating a new article. Everything generated is free and public for everyone to see. I hope you like it and I'm very much open to hearing about new world ideas/features that would make this project better.
My thought: They're trained on so much web content that is plain wrong but authoritative due to apparent endorsement by humans that show tolerance based on understanding which is lacking in an "AI" next-token predictor. Example, https://en.wikipedia.org/wiki/Progressive_web_app "Progressive web apps must use service workers to create programmable content caches." This statement is factually false. There is no requirement that a PWA do this. True is "To create a programmable content cache, a progressive web app would need to use a service worker." But Gemini parrots the false original. I suspect the reason the false original persists as authoritative is the human understanding that subconciously translates it to the true version, theteby tolerating it. If queried, they would acknowledge the original is false. The bot has no such understanding.
Hi HN, I'm Yash, the founder of TabX - a sidepanel extension for Chrome that recalls Chrome tabs by meaning, auto-groups your tabs by intent, offers an AI web search that fetches an ordered list of results for you to act on (while leaving out SEO farms) and much more. I love using the Chrome web browser but could not stand the slow rollout of native AI features within it. "Ask Gemini" can answer a question about the page in front of you but retains no context on the 10 pages leading up to the current page. It is largely reactive rather than proactive. Browsers such as Dia, and Comet have a taken a stab at this but haven't enjoyed strong traction due to high browser switching costs and inertia among Chrome users. I thought, why not augment Chrome, which we love and use every day, with productivity features that make browsing more intuitive and assistive? And hence, TabX! If you're a visual learner, then you can skip the features listing below and watch a how-to video instead - https://youtu.be/HnjxmOHmVik?si=IQupYhxg9gN8gwHd What it does: recall a page by meaning ("That article on Posthog setup I was reading", "The video on Hyrox training from last week"). It retrieves the matching
Confidence, importance, and discussion are three different numbers.
Official and first-party repository changes may publish automatically after deterministic validation. Independent sources remain draft until review. Community links are attached as discussion evidence and cannot create an indexable fact by themselves.
Follow the systems that can break your product or budget.
Save events and hubs locally today. Confirm your email for APIDir research updates, or request team access for entity watchlists, migration alerts, API exports, and webhooks.