Quickly and easily create a CSS grid layout for your website!

typeui.sh is an amazing design layer for AI coding agents! 1. Design skills 2. UI prompts 3. Works with Claude, Codex & Cursor Check it out!

Do you work less or more than before AI?

Co-organizing a builder challenge with @joncphillips: Active Builders x Gradium AI. Free, open to everyone, teams welcome. 1st place wins a Raspberry Pi, 1M Gradium credits and Active Builders lifetime membership. Sign up → activebuilders.dev/hackathon…

Every post on my blog now has a Markdown version for AI agents. Add .md to any post URL and you get clean Markdown. No nav, no scripts, just the content. Fewer tokens, better answers. markodenic.com/discord-code-… Full index: markodenic.com/llms.txt

We teamed up with @GradiumAI to bring this Hackathon to you. Details below!

You have to check this out: 404s.design.

Your AI feature isn't slow. It just waits for the last word before showing the first. Stream it instead: 1. Read response.body 2. Pipe it through TextDecoderStream 3. Append each chunk as it arrives 15 lines. No library. Every modern browser. Full code: markodenic.tech/stream-ai-an…

Most SEO advice is written for marketers. This one's for developers. 7 steps: crawl, index, content, rich results, speed, links, metrics. Plus what to skip and a free PDF. markodenic.com/seo-checklist…

Small update on markodenic.com: long posts now have a table of contents. • It's built from the post's headings, so I don't maintain it by hand. • It only shows on posts with 6+ sections, so short posts stay clean. • It highlights the section you're reading as you scroll. • It's a sticky sidebar on desktop and a collapsible box on mobile. See it in action: markodenic.com/http-status-c…

I built 5 free CSS tools for you: → Text Shadow Generator → Box Shadow Generator → CSS Gradient Generator → Pulse Animation Generator → Border Radius Generator Live preview. Copy CSS or Tailwind. No sign-up. No ads. markodenic.com/tools

If you could choose your next cofounder, who would it be? Mine is @natmiletic!

🫡

Sometimes I get the impression these big AI companies play chess with their announcements. Then I realize, some of them don't know how to play chess.

AI agents are only as useful as their memory. Redis just published a benchmark of agent memory systems using LongMemEval, a benchmark with 500 questions across multi-session conversations. Their Remis + Instruct approach reached 86.5% task-averaged accuracy, the highest result among the production systems they reproduced on a common GPT-4o backbone. The interesting part? It combines two different approaches: ↳ Remis keeps raw conversation evidence using hybrid semantic + lexical retrieval. ↳ Instruct extracts structured facts and updates them across sessions. Together, they cover different failure modes. Redis says the combination matched or beat either approach alone across all six question types in their run. Cost matters too. Redis modeled the combined approach at about $0.07 per session, including answer-LLM costs. They also found that published benchmark results don't always reproduce under the same setup. A useful benchmark to check out if you're building agents with long-term memory. → fandf.co/4hdlNkg — Thanks to @Redisinc for sponsoring this post.