Blog
Notes from real projects on modern web development with Next.js, React and TypeScript, AI integrations with LLMs and RAG, and technical SEO.
425 posts · Page 4 of 21
Anthropic announced the mods system, which lets developers change how Claude Code works, design interfaces and add security rules using TypeScript functions.
Ready-made codes for repairing a yellowed, scratched or black-and-white photo in Gemini. The goal isn't to turn the face into someone else but to make the existing photo legible.
Google unveiled Gemini 4 Argon, its new flagship model with a 1 million token output capacity and advanced cybersecurity capabilities.
Google has rolled out the far more practical Skills system globally in its Gemini assistant, invoked directly with a slash (/), replacing Gems, the customized bots.
Sam Altman said that, as the capabilities of AI models climb rapidly, taking OpenAI public before safety criteria are fully met would create major risks.
Instead of the link clutter of traditional search engines, Perplexity AI gives sourced, instant and direct answers to questions, redefining the AI-powered research experience.
Anthropic announced Claude Sonnet 5.5, the newest member of the Claude 5.5 family. 30% faster and 30% more economical, the model takes the top spot in autonomous coding with a 70.6% score on Terminal-Bench.
Gemini prompts for testing a brand mark. First a text-free symbol, then one color. Don't ask for made-up letters. Draw the wordmark later in a vector tool.
OpenAI announced the Space, Pages and Slides office ecosystem, where teams can create documents, build presentations by voice and work together with AI agents.
Separate Gemini prompts for profile, cover and vertical story. Each prompt has a single subject and room to breathe. Add text later instead of baking it into the image.
OpenAI introduced Dots, AI agents that carry out tasks autonomously on the user's behalf across more than 4,000 apps using a GPT-6 Astra-powered cloud computer and browser.
OpenAI introduced GPT-6.1 Sol, which offers coding and reasoning power at the level of its flagship GPT-6 Astra for one fifth of the price, along with an Ultrafast tier that generates 300 tokens per second.
A voice description, scene note and checklist for narrating a text in Turkish with Gemini 3.8 Flash TTS. The goal is not to memorize a button name but to steer the voice with text.
EVREN, the national AI platform developed by the SSB, is now available with a high-performance Nvidia H200 GPU cluster, a pool of open-weight LLMs and an architecture built around data sovereignty.
The Vercel app is a hosting service that builds the Next.js project in your Git repository and publishes it at an address. To start for free you need an account, a repository and a first deployment.
Three HTMX patterns: submitting a form without a page reload, returning HTML fragments to a search box and loading tabs from the server. Each example uses a single feature.
OpenAI is getting ready to announce a $500-a-month Pro Max plan for ChatGPT, with Cerebras infrastructure, high inference speeds and autonomous tasks at the forefront.
Jev does not generate chat text. It returns a defined decision and a confidence score. In the first example it picks a route, and if the score is low the request goes to a larger model or a human.
Microsoft Copilot has been redesigned from scratch; with the Home, Code and Autopilot tabs it combines natural-language app building, autonomous agents and consumption-based billing.
TypeSafe AI has left behind the slow, hallucination-prone design of classic LLMs and announced Jev, a System One decision model that is 200 times faster with zero type errors.
xAI has announced Creator Rewards, a program that pays developers building AI bots and agents on the Grok Bot platform every two weeks.