If you're still copy pasting your markdown files and not using the Agent Zero live editor canvas, you're falling behind with AI. Ask your agent to create, or open a markdown document artifact in the right canvas. Then ask for edits and start coworking. @Agent0ai

✅ #1# requested dev feature shipped: Markdown API! In the last year, we shifted our focus and launched many of your top asks like: - Database views API - Personal access tokens - Notion MCP is 91% more token-efficient - Root page creation - Database locks for read-only - Database templates - AI Meeting Notes API - OAuth scoped to your workspace - Developer Portal And, we have a lot more in store for you.

NEW: Metaplanet reported Q1 FY2026 revenue of ¥3.08 billion, up 251% year over year, as the firm continued aggressively expanding its Bitcoin treasury strategy. Operating profit rose 282.5% YoY to ¥2.27 billion, according to results shared by CEO Simon Gerovich. The company also reported a 73.6% operating margin and a 2.8% BTC yield for the quarter. Despite strong operational growth, Metaplanet posted a net loss of ¥114.5 million due to non-cash Bitcoin valuation adjustments tied to BTC price fluctuations. The results highlight how accounting treatment continues to distort earnings for Bitcoin treasury firms. Metaplanet previously reported an FY2025 net loss of roughly ¥95 billion, largely driven by a ¥102.2 billion non-cash Bitcoin markdown.

This works really well btw, at the end of your query ask your LLM to "structure your response as HTML", then view the generated file in your browser. I've also had some success asking the LLM to present its output as slideshows, etc. More generally, imo audio is the human-preferred input to AIs but vision (images/animations/video) is the preferred output from them. Around a ~third of our brains are a massively parallel processor dedicated to vision, it is the 10-lane superhighway of information into brain. As AI improves, I think we'll see a progression that takes advantage: 1) raw text (hard/effortful to read) 2) markdown (bold, italic, headings, tables, a bit easier on the eyes) <-- current default 3) HTML (still procedural with underlying code, but a lot more flexibility on the graphics, layout, even interactivity) <-- early but forming new good default ...4,5,6,... n) interactive neural videos/simulations Imo the extrapolation (though the technology doesn't exist just yet) ends in some kind of interactive videos generated directly by a diffusion neural net. Many open questions as to how exact/procedural "Software 1.0" artifacts (e.g. interactive simulations) may be woven together with neural artifacts (diffusion grids), but generally something in the direction of the recently viral There are also improvements necessary and pending at the input. Audio nor text nor video alone are not enough, e.g. I feel a need to point/gesture to things on the screen, similar to all the things you would do with a person physically next to you and your computer screen. TLDR The input/output mind meld between humans and AIs is ongoing and there is a lot of work to do and significant progress to be made, way before jumping all the way into neuralink-esque BCIs and all that. For what's worth exploring at the current stage, hot tip try ask for HTML.

Weird isn't just visual. Weird is whatever strays from the norm. Weird is relative to the current state of the world. You can have weird principles. They should be things people can legitimately disagree with. You have to remember Obsidian was very weird when it launched six years ago. Local files, malleability, backlinks, graph, even Markdown syntax... these were not as widely understood and accepted as they are today. That's why I spent so much time writing essays like "File over app" to try and explain our choices. The goal was to describe why our weird ideas should be normal, and it worked! Now the world has somewhat caught up and accepted those choices, so it's time to find the next frontier of weirdness.

Since the research preview in February, hundreds of organizations have used it on production code, catching issues existing scanners had missed. Based on early feedback, we've added scheduled scans, directory-level targeting, CSV and Markdown exports, webhook notifications for new findings, and dismissals that carry forward across scans.