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

Muse Spark 1.3 is now in Codex!! OpenCode's free... tier runs it for nothing, and $10 on OpenCode Go gets you over 45,300 requests. It's basically Opus 5 tier too. There's a catch though. Meta may use your inputs and outputs for training, which is the whole reason the tier is called contributor and the whole reason it's free. Muse 1.3 just sits in the picker next to my paid models now. I'll just use Astra + Muse Spark for subagents. Gonna keep everything in stock in case we need it.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

if you use Codex and you're stuck on GPT... models only, this fixes that. it's called codex-router, open source. drops other models straight into your normal Codex picker, right next to the GPT ones you already have. what it adds: - Grok, Kimi, Deepseek, Claude, all in the same picker - oauth login per provider, no api key needed - your GPT models and Chatgpt login stay untouched setup: point Codex at the repo, let it read the readme, it installs itself one snag: if you've got the Chatgpt app and a separate Codex on your path, you can end up running two different Codex versions, and the older one can choke on newer config it doesn't recognize. if the install looks off after, that's probably why, reinstall clean.show more

"You've reached your rate limit. Try again after 7pm."... every. fucking. day. $200/month - $2,400 a year - for Codex. then i opened the DeepSeek pricing page. Someone made DeepSeek a native subagent for Codex. Heavy work goes there, light stays on GPT-5. Same code out the other end. 35x cheaper. DeepSeek V4 Flash lives on its own API key, not on my Plus quota. One command: npx skills add oil-oil/codex-deepseek-subagent -g -y Restart Codex, tell it "set up DeepSeek as a subagent", done. First day in a month I'm still working in the evening instead of hitting the wall. save this before your next rate-limit ↓show more

this is literally f**king insane i just 2x my... usage limits on $200/mo codex i figured out how to use deepseek v4.1-flash on $10/mo opencode go for routine subagent work... while gpt-6 astra directs the project and sol handles implementation. here's how to set it up in 3 mins: → connect opencode go to codex through model-router → install quota flow, including its skill and agent profiles → open a fresh astra task and paste: quota flow tells flash to handle discovery and checks, sol to implement, and luna to review when needed. the same implementation agent keeps its context through the build → test → fix loop. every extra agent should earn its call.show more

Okay this is kinda wild 👀 NVIDIA is basically... handing out FREE API keys to 100+ top AI models - GLM 5.2, DeepSeek V4, Kimi K2.6, MiniMax M3, their own Nemotron and a ton more. it's called NVIDIA NIM and I had no idea it existed. it's rate-limited, so not something you'd run in production - but for personal use it's honestly great. you can poke a dozen frontier models, and some you can even grab and self-host. dropped a key into OpenCode and it just worked. the hyped ones like GLM 5.2 are jammed with queue right now, but the lighter models fly. all of it free.show more

Fable 5 dropping again is the biggest AI moment... of the year. It’s also a usage limit trap if you don’t know what you’re doing. I just mapped out the full system to run it at 10x lower cost: - 10-80-10 framework - Model routing table - Loop engineering - Codex setup - Context memory - And every mistake that burns your limit in the first hour Don’t open Fable again until you read this.show more

Every AI tool wants its own subscription. We built... ours around a token you already hold. Stake once and it earns Sorin credits at 1 per $SAHARA every month, on top of the 3,500 every user gets free. The same stake earns Sahara compute credits next, spendable inside ClawApp or straight through our API. Every product we add plugs into that stake, and there is never anything to restake. And you keep the SAHARA the whole time. Unstake whenever you want and you walk away with everything you came in with. Own your compute.show 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

40k. I am grateful for each and every one... of you. As a thank you, I've made 40% off for the next 40 hours. If you've heard about it or been waiting to join, now is the time!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

sorry, they just did WHAT someone gave a machine... one disease name, the leading cause of blindness in the developed world with 1.5 million americans already in its path, and it came back pointing at a drug that has sat in pharmacies for years under a different label: 551 papers read in 30 minutes against the 294 hours a human would have needed, and the loop that did it is public on GitHub most agent setups answer one question at a time, so the ceiling on the work is the quality of the question you happened to think of this one was handed a single question and wrote the second one itself. turns out that follow-up is where the real find was: a target called ABCA1, upregulated threefold, in an experiment no human ordered i read the whole paper looking for the trick, and the trick is structural. that is the second question, and it is the gap between an assistant and a factory: - hand the loop a field rather than a task: it was given a disease, and choosing the mechanism was part of its job - make it rank before it spends: 151 papers in, ten candidate mechanisms out, scored against each other before anything touched a bench - split reading from judging, so the agent that forms the theory is a different agent from the one grading it - close every cycle on physical reality: the verdict was an experiment, and another model's opinion was never allowed to stand in for one - feed each result back as the next question rather than a log line, which is the step almost nobody builds - search what already passed inspection first: the winner was an approved compound with a safety file already on record - write down what the round learned before opening the next one, so round two starts where round one stopped my read, and i think it is the uncomfortable one: reading was the entire bottleneck in that field, and everybody spent the decade optimising the writing. people ran every physical experiment here, the analysis agent needs a domain expert writing its prompts, and the authors decline to call this the leap it resembles. the thinking got replaced, and the hands did not so the question i cannot answer for my own setup: which step of your loop still stops dead until you sit down and type something bookmark this one. the four parts that turn one model into a line that runs like this, the queue, the rooms, the write permissions and the gate, are built file by file in the piece below ↓show more