Show HN: Captcha to detect bots with a simple question https://ift.tt/93yBre5

Show HN: Captcha to detect bots with a simple question https://joshryandavis.github.io/dumb-captcha/ April 9, 2026 at 07:14PM

Show HN: I built Dirac, Hash Anchored AST native coding agent, costs -64.8 pct https://ift.tt/0oW9Lny

Show HN: I built Dirac, Hash Anchored AST native coding agent, costs -64.8 pct Fully open source, a hard fork of cline. Full evals on the github page that compares 7 agents (Cline, Kilo, Ohmypi, Opencode, Pimono, Roo, Dirac) on 8 medium complexity tasks. Each task, each diff and correctness + cost info on the github Dirac is 64.8% cheaper than the average of the other 6. https://ift.tt/WgNDIsO April 9, 2026 at 05:36PM

Show HN: CSS Studio. Design by hand, code by agent https://ift.tt/JTk0epf

Show HN: CSS Studio. Design by hand, code by agent Hi HN! I've just released CSS Studio, a design tool that lives on your site, runs on your browser, sends updates to your existing AI agent, which edits any codebase. You can actually play around with the latest version directly on the site. Technically, the way this works is you view your site in dev mode and start editing it. In your agent, you can run /studio which then polls (or uses Claude Channels) an MCP server. Changes are streamed as JSON via the MCP, along with some viewport and URL information, and the skill has some instructions on how best to implement them. It contains a lot of the tools you'd expect from a visual editing tool, like text editing, styles and an animation timeline editor. https://cssstudio.ai April 9, 2026 at 04:53PM

Show HN: I built a local data lake for AI powered data engineering and analytics https://ift.tt/Uodh2BO

Show HN: I built a local data lake for AI powered data engineering and analytics I got tired of the overhead required to run even a simple data analysis - cloud setup, ETL pipelines, orchestration, cost monitoring - so I built a fully local data-stack/IDE where I can write SQL/Py, run it, see results, and iterate quickly and interactively. You get data lake like catalog, zero-ETL, lineage, versioning, and analytics running entirely on your machine. You can import from a database, webpage, CSV, etc. and query in natural language or do your own work in SQL/Pyspark. Connect to local models like Gemma or cloud LLMs like Claude for querying and analysis. You don’t have to setup local LLMs, it comes built in. This is completely free. No cloud account required. Downloading the software - https://ift.tt/J6UHuAV Watch a demo - https://www.youtube.com/watch?v=C6qSFLylryk Check the code repo - https://ift.tt/d1XPahV This is still early and I'd genuinely love your feedback on what's broken, what's missing, and if you find this useful for your data and analytics work. https://ift.tt/zvfxTBG April 9, 2026 at 02:41AM

Show HN: Skrun – Deploy any agent skill as an API https://ift.tt/J9mILFq

Show HN: Skrun – Deploy any agent skill as an API https://ift.tt/p0RxwoZ April 8, 2026 at 06:04PM

Show HN: Orange Juice – Small UX improvements that make HN much easier to read https://ift.tt/bIpNPvy

Show HN: Orange Juice – Small UX improvements that make HN much easier to read http://oj-hn.com/ April 8, 2026 at 11:38PM

Show HN: Unicode Steganography https://ift.tt/UqrizRl

Show HN: Unicode Steganography I built a demo of two Unicode steganography techniques, zero-width characters and homoglyph substitution, in the context of AI misalignment. The first is about the use of two invisible zero-width characters (ZWS and ZWNJ) to binary encode text. The second is much cooler. Most characters in the Latin and Cyrillic alphabets look nearly identical, but have different unicode. If you have text to encode and convert it into binary representation (1s and 0s), you could take plain english "carrier" text and for each 1 in the binary representation you could substitute the Cyrillic letter equivalent. Decoding the message requires traversing the text and seeing where Cyrillic letters could have been substituted but weren't, and where they were, leading to 0s and 1s respectively, which can be built back into your original hidden text. In both cases, these are detectable, but the interesting problem for me is whether an LLM could eventually invent an encoding that goes unnoticed by both us, and automated detection. If LLMs were able to covertly include messages in plaintext, misaligned AI Agents could eventually communicate across MCP/A2A and individual chat session boundaries undetected. A deceptive LLM might seem helpful, but work against your goals. It could tell other agents it interacts with over MCP/A2A to help it discreetly fail, signal intent, and avoid tripping oversight/safety mechanisms. Furthermore, oversight mechanisms become more difficult to implement if we can't believe our own eyes. https://ift.tt/OVetC9r April 7, 2026 at 06:27PM