OpenCode Go is now wired into Codex!! The pricing... is insane. $10 gets you 10,000 DeepSeek requests every 5 hours (no weekly limits). I converted that into DeepSeek API dollars because I thought I was reading it wrong, and the same 5 hours of usage would run somewhere between $10 and $30 depending on how big your context gets. So one afternoon of use already covers the whole sub. It comes with Kimi K3 as well. Both sit in the picker next to my other models now. Next time we hit a limit in the middle of a loop, we can grab it and keep going.show more

Codex can run Qwen-3.8-max now as well!! Alibaba most... capable model, dropped today and it's already in my codex picker. It's a token plan subscription, not metered api billing. You take the key from your Qwen plan, drop it into Codex Router, and it spends down the plan instead of your card. There's a catch though. Qwen's official setup switches your whole codex over to them, so your ChatGPT models stop showing up at all. That's exactly what Codex Router is for. It adds models to the list instead of replacing them, so sol, Grok, kimi, Deepseek and now Qwen 3.8 max all sit in the same picker and it can grab whichever one suits the job. Router's open source, setup's in the video 👇show more

Codex can now run Deepseek-v4- flash! There's a catch... though. Deepseek's official setup switches your entire codex over to them, so your GPT models stop showing up at all. This is exactly what Codex Router is for. It adds models to the list instead of replacing them, so sol, grok, kimi and deepseek all sit in the same picker and i just grab whichever one suits the job. Deepseek v4-flash is $0.28 per million output tokens. opus 4.8 is $25. same picker, 89x apart. Links in the comment. setup's in the video 👇show more

holy sh*t this is f**king dangerous i just figured... out how to run Opencode in Codex It has Deepseek V4 Flash which replaces Opus 5 at 1/4th price You can get 10,000 request in only $10/month along with Kimi K3 and Qwen 3.5 Max [here is how you set it up] 1. install the 'codex-router' 2. Put in the Opencode Go API key 3. Done that's it Save this no matter what. This will be the best thing you do this weekshow more

GPT-5.5 is MUCH more reliable on longer running tasks... - for the first time with any model. As we speak I have a migration running for over 7+ hours - this literally never happened before, the models would maybe run for 30 mins or of you really shout at them for 2-3 hours. Last night I went to sleep, set a long running task, then queued up 10 prompts to 'keep it going'. It did not stop after the first prompt and kept going for 8+ hours and I woke up to all the same prompts still queued up. The ability to run for a long time, in combination with ability to validate with computer use & other tools, makes it much more useful for building real applications.show more

DeepSeek R1 is *the* best model available right now.... It's at the level of o1, but you can use it for free, and it's much faster. A huge leap forward that nobody saw coming. No wonder so many people are throwing tantrums online trying to discredit the Chinese students who built this. You can use DeepSeek in Visual Studio Code right now: 1. Install the Qodo Gen AI extension 2. Select DeepSeek R1 from their list of models The Qodo team is hosting DeepSeek on their servers, so none of your data will go to China. I've been building a Tetris game using DeepSeek, and this is the most impressive model I've seen so far.show more

Read Caption 💗🥺 ❄️ People always ask me why... I skate. I skate because out of every sport I have ever tried, this is the only one that taught me something real. No matter how many times you fall, you have no choice but to get up again. Figure skating found me during a time when I was discovering myself, healing myself, and rebuilding the parts of me I thought were gone. It became something that no one could ever take away from me. I am passionate about this sport because of what it does to my soul. The moment my blades touch the ice, something in me settles. I feel whole. I feel protected. I feel like I have entered a world where nothing can break me. No one can walk into that space and dim my light or tell me I am not enough. On the ice, I define myself. Figure skating is a place where applause comes from every direction, even from within. You clap for your effort, your courage, your growth and even bad days. You get to watch yourself evolve in ways you never imagined. It is mesmerizing to witness how far we can go when we keep moving, when we trust the process, and when we simply skate. When I skate, I am reminded that my journey is mine alone. Every glide is a voice saying I survived. Every spin is a reminder that my spirit still dances. Every fall becomes a lesson in strength, and every landing becomes a quiet celebration. Skating taught me how to breathe again, how to trust again, how to see myself again and how to love the person I am becoming. And that is why I keep going back to the ice, again and again. ❄️ ✨ #figureskating #health #healing #iceskatingshow more

This seems like it would be on an episode... of “I Shouldn’t Be Alive,” you and your friend go to the mall to get a nice outfit for an outing later. The department you need to go to is on the second floor, so you and your friend decide it would be quicker to go on the escalator. All of a sudden as you are approaching the middle of the escalator, you hear the escalator come to a screeching halt. You and your friend are now stranded in the middle of the escalator. Every second counts, it’s been two hours now since you’ve had food or water since you e been stuck on the escalator and time is ticking, do you risk an escape plan?show more

1-bit Kimi K3 performs at Opus 5 level on... 3D physics! We ran our Atomic Chat quant of Kimi K3 locally on 4x B200 against three cloud models and gave them all the same task, to build a giant anvil drop test as a single HTML file with real physics Outputs: K3 1bit (local): 15.8K tokens, $0 API cost Kimi K3 (API): 15.3K tokens, $0.30 API cost Opus 5: 22.8K tokens, $0.77 API cost GPT 5.6: 14.5K tokens, $0.72 API cost All four got the physics right. But only Kimi made a working winch. The drum turns and the chain drags the flat car off the pad. Opus 5 drew the most detail, road markings and sparks on the hit. And you can run a model at this level on your own box now. That still feels insane to usshow more

A tale as old as time. Who is at... fault. You’re driving along when a Jeep in another lane makes a swift maneuver and gets in front of you in your lane. Because of the speed you were maintaining, now you’re technically tailgating. However, the Jeep suddenly slams on its breaks and you run into the back of it. So who is at fault. Who does the insurance believe is at fault. Because you had a dash cam the Jeep was found at fault but if that cam wasn’t there would it be the same outcome.show more

Making OpenCode as lean as Pi agent? Just trimmed... 25k out of OpenCode's system prompt (from 30k to 4-5k tokens) How? Just disable skills and get rid of massive skill definition bloat. Who needs skills anyway? Just kidding, this is the not the way. It makes the agent lame and defeats the point of using one. But it sets a precedent: Find a way to use skills without their definitions pre-loaded into the system prompt every single turn. Another interesting stuff: Upon testing this temporary "no skill setup" with two of hottest OpenCode Zen free models, Mimo V2.5 vs DeepSeek V4 Flash: One thinks more and talks less One thinks less and talks more Check the video to see which is which If you made it here, I'm finding a way to leanest OpenCode setup that I can get I simply don't believe that OpenCode can't be as lean as Pi Upon tinkering, I made a plugin that temporarily extracts the system prompt while I test, and noticed the hundreds of definitions in it from my .agents/skills directory which is shared across all my coding agents (Cursor, Antigravity, Claude, etc.) Of course disabling skills is not the answer, but it just proved that there is a way to strip the system prompt of these massive skill defs Aside from the system prompt hierarchy that injects confusion imo if you have a conflicting and redundant AGENTS.md which I discovered upon digging into OpenCode's source code Apparently it has prompt.ts/system.ts/instruction.ts/llm.ts and loads base .txt prompts based on model family (claude/gpt-o/gpt-5/codex/gemini/others) that all work together to make OpenCode aware of who it was and how it should use tools and become a "coding agent" Gotta find the most minimal mix that fits right into my workflow Make OpenCode as lean as Pi? We'll see. All inshow more

We are not a web3 company doing a game.... We are gaming studio in love with web3 and the blockchain technology bringing the best actors of both worlds to work together to create a series of absolute gaming hits. We have people from Epic games, Activision, Pixar and Disney currently working on this and are now raising 10 millions to bring it to the next level. We don't just want The Mories to be one of the next big IPs. We want to become the next Ubisoft and have The Mories be the main IP of it. You can fade. Or not. It doesn't matter. We will make it.show more

I look at all markets. Sectors, asset classes, bonds,... metals, energy, and sentiment. Why? Because there is a finite amount of liquidity in the system, and it all has to go somewhere. The main driver is fundamentals, but every now and then, macro comes into play. We have literally gone straight up for the last 6 weeks. Sure, it might be time for a pullback, but it was also time 2 weeks ago. However, let’s not kid ourselves, the last 6 weeks have been the most outstanding performance of my our career. You can never sell the top, and you’ll never catch the bottom consistently. My best ideas have done VERY well YTD and have had breakneck rallies in the last 6 weeks. No, I didn’t go all in on software. I also didn’t go all in on oil stocks at the worst time possible or FOMO into $NBIS or $MRVL today. I have been looking hard at leading themes every day. No breaks. That is exactly what I do. And I love it. I learn every day from everyone. There are so many people to thank, but the job is not over. The job is never done. Keep going. Whether long, short, flat… just keep going. I ALWAYS will. This is my vow to the community. God bless. 🫡show more

I didn't realize how much time I was wasting... until I stopped having to type the same instructions every single time. Every prompt looked something like: – Use our colors – Match the existing UI – Keep it responsive – Follow accessibility best practices Now I just save it as a Skill in. From then on, it remembers the context for me. It's one of those features you don't think you need... until you use it once.show more

oh let's DO IT 🔥 On Air Romeo is... now tapped in and taking your requests over the next 5 HOURS!!! 👏 So, who can we play most for you tonight from coast to coast to coast on #MostRequestedLive? Let us know! 🤩show more

AI’s next frontier is Spatial Intelligence, a technology that... will turn seeing into reasoning, perception into action, and imagination into creation. But what is it? Why does it matter? How do we build it? And how can we use it? Today, I want to share with you my thoughts on building and using world models to unlock spatial intelligence in this essay below. 1/nshow more

Claude Mobile starts the idea... Ghostty finishes it I... basically use Claude Mobile as a notepad now. Whenever something comes to mind, I open the app, pick a repo, and ask Claude to start exploring. Then I just let it run while I go on with my day. Later I jump into Claude Desktop and I’m right back in the same session, with context, structure, and a clearer shape of the idea. I tweak a few things to set up the coding phase. Finally, one click to Ghostty (video), open a couple of worktrees, and start working on the PR. IMPORTANT: when you move to Ghostty, it must be the exact same repo you started on mobile, otherwise the --teleport command will failshow more

1 Neural Network + Obsidian + Karpathy’s 1-file method... = the most unhinged second brain build of 2026. It remembers everything you’ve ever done, and it costs $0 on top of what you already pay. The base is Karpathy’s append and review: 1 giant note, new thoughts stack on top, old ones sink, every few days you reread and pull the survivors back up. No folders, no tags, no plugins the rereading IS the system, because review is what turns storage into thinking. The flaw: past 10,000 lines, no human rereads anything. That’s where the neural network takes over. You keep the note in Obsidian 1 vault, everything dumps to the top: ideas, links, meeting fragments, half-thoughts. You never organize, you only dump. It all lives as plain markdown on your own disk, and that detail is the whole trick. Because now you point Claude Code at the vault folder, and it reads every line you’ve ever written. “What did I think about pricing in March.” “Find the 3 ideas I keep circling.” “What did I drop that deserves a second look.” It answers from YOUR notes, with quotes, in 15 seconds. Then once a week, 1 prompt closes the loop: read the last 7 days, surface the 5 entries worth pulling back up, flag anything that contradicts what I wrote a month ago. The model does the sinking and surfacing Karpathy did by hand, and the note stays alive instead of turning into a graveyard. Week 1 feels like nothing. Week 4 you hit the first “I already solved this in January.” Month 3 you consult your past self more than Google. Most second brains die in 11 days under 40 plugins and 200 folders. This one is 1 file and a loop, and it compounds because dumping takes 0 discipline. Notion stores what you thought. This thing argues back.show more

Flipping houses, or rehab and resell, is a game... that seems to be the craze these days. People with little (myself) or tons of money think they can buy a dump of a house, shine it up, and make $100,000 without a problem. So, I gave it a try, putting my proverbial chips in the middle and going all in. Renovated it in 63 days. New roof, HVAC system, electrical panel, kitchen, bathroom, doors, trim, flooring and paint. I listed it, and then it just sat—hours, days, weeks, months — costing me $100 per day in holding costs. We adjusted the price, staged furniture, and reshot photos, but it sat, but why? The basement was wet, which is the kiss of death in real estate, I have learned. As a GC, I have access to a network of subcontractors and skill sets that many people don't, though that doesn't mean repairs are free. After spending $60,000 in renovations, $14,000 in closing costs, and $32,000 in holding costs I was taking a loss on selling this house. Then, I had to put another $15,000 into it to stop water from entering the basement. It is what it is. The house is now under contract, and we feel good about things, which is a distraction from the other house I bought in the middle of all of this until my guy sent me this video yesterday as he was leaving….show more