Instead of paying $2,000+ a month just to feel like you work at a hedge fund, what if you could have a Bloomberg terminal without paying Bloomberg terminal money? That’s the idea behind OpenTerminal, our favorite new GitHub project for the finance nerds. It pulls together stock and crypto prices, candlestick charts, technical indicators, sector heatmaps, screeners, options chains, macro data, yield curves, market news, and more into one self-hosted terminal built entirely on free public data sources. It even has a Claude assistant that can help explain what’s happening on your screen. It’s not actually Bloomberg-level market infrastructure, but for personal research, it’s a pretty ridiculous amount of terminal for $0. We look forward to everyone with $43 in Robinhood becoming a macro strategist. GitHub:

We gave AI 20 dollars to make a fake UGC ad. A few minutes later, we had one. Then 10. Then 100. Then 1,000. @slop_pig breaks down how AI can flood feeds with fake people, fake recommendations, and content tailored to look organic.

Prompt highlight of the week: Someone built a library of motion graphics made with Claude Opus 5.5, with every animation shown next to the exact prompt or skill that made it. There are 226 examples so far, with each pulled from posts on X and credited to the original creators. The next time you need to spice up your videos try using one from

The most confusing SF "billboard" of the week, this week won by @arceuslegal we support more start-ups having cute and cuddly mascots if you see a billboard that made you stop in your tracks DM us for a chance to win next week's billboard of the week

What if your AI coding agent could remember every bad idea it already tried? 👇 That’s basically the idea behind ergon-wrong-turn-logger, our favorite new GitHub project. Every time you or an AI takes a wrong turn, you log what happened, what broke, and what you should have done instead. Those failures then live in a database instead of disappearing when the task ends. So months later, you can ask: have we tried this before? And instead of starting from zero, you get the clues from the last failed attempt. As coding agents take on more work, teams will need a persistent memory layer for what failed as well as what worked. It serves as institutional memory for AI agents. Ultimately, we look forward to Claude developing generational trauma from every failed refactor. Link to the project here:

We went to the California desert with a startup building UFO detection systems. They invited a group of psychics who believe they can communicate with UFOs. It got weird. Our full documentary on @eldaeonuap and America's UFO tracking industry is out now 👇 00:00 The American UFO detection industry 01:00 Inside Eldaeon, the company building a UFO detection network 02:05 Nemesis is their $500 personal radar system 02:29 What is passive radar? 03:29 Testing Nemesis at LAX 04:44 Heading out on a psychic mission 05:54 How did David become a UFO engineer? 07:58 Setting up a $25,000 UFO tracking system 09:13 US government support 09:35 How the $25,000 tracking system works 10:29 Meeting the Australian psychics who say they communicate with UFOs 11:24 What is "psionics" 13:36 UFO... or satellite? 15:32 Starting the UFO psychic mission 16:56 A sighting? 17:48 Unusual technical glitches 18:55 An intense psychic connection 20:09 Mission debrief

Really glad to work with a frontier tech like this! Happy to see our sim/game become a real robot pilot training arena. The whole team worked really hard for REK2 event, I was there DJing the pre show and the fights and it aaaall happened smoothly! On to the next one! Follow @REK