Radical Ed 𐤊

dagknight v0 devnet progress doesn't stop branch live on the rusty-kaspa repo - checkout the r&d telegram for more info

1/ Denmark was reportedly preparing for full-scale war with the US over Greenland in January, with military support from France, Germany, and Nordic nations. Elite troops and F-35 jets with live ammunition were sent, and runways were to be blown up to prevent an invasion. ⬇️

Because it's often getting lost in the discussion here, this is a partial list of Iran's attacks on energy *before* the Israeli strike on South Pars: - Ras Laffan LNG complex in Qatar - Ras Tanura oil refinery in Saudi - hundreds of drone attacks on Saudi oil fields - Ruwais refinery in Abu Dhabi - Shah gas field in Abu Dhabi - port of Fujairah - Bapco oil refinery in Bahrain The list goes on. Point is that, yes, South Pars was an escalation in American/Israeli targeting, but it comes after weeks of Iranian attacks on GCC energy infrastructure.

This is what a one-person AI Agent run company looks like in 2026. 6 AI agents. 20 cron jobs. 0 human employees. Every role is a folder. Every job description is a md file. No standups. No Slack. No payroll. Just a directory on a Mac that runs the whole thing.

🚨 I found a GitHub repo that just killed RAG for agent memory. It's called Hindsight. And it just hit SOTA on the LongMemEval benchmark beating every memory system ever tested. Most agent memory systems are just glorified vector search. Store a chunk, retrieve a chunk. That's it. Hindsight does something completely different. It uses biomimetic memory structures the same way human memory actually works: → World facts ("the stove gets hot") → Experiences ("I touched it and got burned") → Mental models (learned understanding built over time) Recall runs 4 retrieval strategies in parallel: semantic, keyword, graph, and temporal. Then merges and reranks everything. The result? Agents that don't just remember. They learn. MIT License. 100% Opensource. Link in comments.

hey if you have a 3060, or any GPU with 8GB or more sitting in a drawer right now, that thing can run 9 billion parameters of intelligence autonomously. and you don't know it yet. 2 hours ago i posted that 9B hit a ceiling. 2,699 lines across 11 files. blank screen. said the limit for autonomous multifile coding on 9 billion parameters is real. then i audited every file. found 11 bugs. exact file, exact line, exact fix. duplicate variable declarations killing the script loader. a canvas reference never connected to the DOM. enemies with no movement logic. particle systems called on the class instead of the instance. fed that list as a single prompt to the same Qwen 3.5 9B on the same RTX 3060 through Hermes Agent. it fixed all 11. surgically. patch level edits across 4 files. no rewrites. no hallucinated changes. game boots. enemies spawn, move, collide. background renders. particles fire. and here's what nobody is talking about. this is a 9 billion parameter model running a full agentic framework. Hermes Agent with 31 tools. file operations, terminal, browser, code execution. not a single tool call failed. the agent chain never broke. most people think you need 70B+ for reliable tool use. this is 9B on 12 gigs doing it clean. the model didn't fail. my prompting strategy did. the ceiling is not the parameter count. the ceiling is how you prompt it. this is not done. bullets don't fire yet. boss fights need wiring. but the screen that was black 2 hours ago now has a full game rendering in real time. iterating right now. anyone with a GPU from the last 5 years should be paying attention to what is happening right now.