Michael Arnaldi suggested cloning the effect repo as a... git subtree, giving it to Claude, then using that as docs It sounds absurd, but it's actually kind amazing lol Setup a custom OpenCode agent that has all the context on where the files are then it kinda just works I feel like this could definitely be refined but idk if I even care enough. Stuff like cursor/opencode/claude code is already so good at searching codebases that I don't really care to do anything moreshow 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

Tradermayne uncovers that plasma:native is printing one of the... most reliable setups. "I think it goes to 12 cents in the next two weeks, but I don't have a position, so I don't really care. I like this three-day chart setup. This is a really, really strong setup. This is a quarterly low that got swept, and then it broke structure the other side." Feat. Mayne Ponzi Trader Kraken Proshow more

While I have premium I definitely want to do... a long post breaking down the main scene from this show that I obsess with. There's so much that I feel could be learned from it. Not just for expansion animators either. There's honestly a LOT that can be learned from how this show directed its expansion scenes that can be applied to even safe for work animations. Obviously yes, the expansion alone is really good. What makes it so good though is just the fact that there's things you pick up on that you likely don't even realize until you re-watch. I'm using this scene as an example as it's not AS good I would say, but it still has a lot going for it. One thing I've always loved from it that I want to use in my own animations someday is that the expansion sort of comes in waves as opposed to one consistent growth. In a way, it makes it feel more natural while also selling how tight the top is getting. It could have been accompanied by showing the knot getting tighter or smaller with each growth. It's a small part of the animation but just that one thing already adds another layer to appreciate. It's not like most expansion scenes where there's very little outside of just "growing" on its own. There's a bunch of little things that subtly improve it without being obnoxious. The first expansion scene has WAY more that I want to talk about honestly. Far more than this one has. It will probably be a really long post now that I think about it...show more

🐯: I also realized, in my life, that plants... are actually this hard to take care of… after trying to grow them myself. 🐯: Since I’ve been taking care of them, it doesn’t feel like I’m alone at home. It keeps me a bit busy 🐯: I actually had a bit of separation anxiety in my 20s, so I didn’t like being alone 🐯: So I used to keep bringing friends over all the time, but now, I kind of wish they wouldn’t come as much 🐯: Even just taking care of plants alone is already a lot. They all kind of have similar personalitiesshow more

Hot Take: DLSS5 lets Nvidia make the games look... almost too different. (In the case of Wuwa, the environment is fine, but the characters... hell nah.) At that point, should the game devs even care about art style? If Nvidia just alters it to something that doesn't even look like the game itself? (also it tooks too AI....idk man) I don't really like DLSS5. I know they will release it fully later, but I don't know, man, I don't have a good feeling about it. #WutheringWaves #WuWa #Nvidiashow more

I have a little robot that unlocks my door... from the inside (so I don't have to carry a key) The problem was it wouldn't calibrate on my door. It was designed for 90° turns, but my lock only needs 15° In the past, this would've been a showstopper But I asked AI if it could help... At first, it suggested I snoop on the bluetooth connection to figure out the protocol Then it realized that we could probably just decompile the app's SDK and read its source code. That worked! It told me to switch to my mac and run some python for it. Unfortunately, it couldn't run the scripts directly because Claude Code Desktop didn't have bluetooth permissions, but my shell did. Thinking about it now, I probably should've used Claude Code or Codex in the Terminal. Anyways, it took a while, lots of backs and forths, we had some misunderstandings, it was massively overcautious in the beginning, but we finally got the lock calibrated! Feels like magic! I threw the repo up on github in case anyone in the future (ie me) runs into a similar issue – hopefully it can save them some timeshow more

behind of yesterday’s tiktok ⭐️ 🐰 the ‘tree’ challenge... that i did yesterday…i did it because i wanted to 🐰 as soon i saw it, i was like “i need to do this” it’s so funny 🐰 that’s actually not what i was going to film that day, it was supposed to be a sexy challenge but i’m not really good at those kind of challenges where you have to be like “look at my sexiness”, even with performances i prefer doing something that’s more light so i told them that there was something else i wanted to do instead of that one and they asked me what i wanted to do so i showed them the ‘tree’ challenge and said that that’s what i wanted to do 🐰 we actually save the ones that we’d like to do and bring it with us so we can show it to them 🐰 when i showed it to them, they loved it and were like the “let’s do this! let’s do it right away!” 🐰 i wasn’t going to film a challenge that day so it was a very sudden filming and i was wearing sandals…something like slippers with nothing covering my heels so they kept coming off my feet when i was doing the step 🐰 i think i filmed it about 5 times, i filmed it many times 🐰 “you should’ve done the sexy one” i mean…i can do it if i have to but i’m not good at it…doing something sexy on stage is fine but being like “wow look at me 😏” is not something i particularly like either 🐰 i like doing light performances and i think that’s what suits me as well 🐰 each person has something that suits them 🐰 yeonjun hyung & beomgyu are excessively coy when they’re on stage and they’re people that suit that kind of thing but i feel like i’m not someone that suits it 🐰 i think i suit light concepts better 🐰 i don’t know about suiting because everyone will have a different opinion but i personally like that better!show more

Claude Code Desktop now opens a new window for... each session This makes it much easier to visualize multiple Claude Code agents running in parallel My current stack depends on the task: - Ghostty: when starting a project. Bash commands, git, env variables, provider connections. All manual through the terminal with a Claude panel running alongside. - Claude Code Desktop: once everything is configured. GitHub connected, CLAUDE.md, Skills, subagents and Hooks ready. Claude Code runs on its own, no more terminal setup, just panels running and outputs to review. - VSCode: when I need to review code by hand. I use it less and less, but there are moments where I have to confirm Claude got it right. I usually open the Claude extension inside VSCode, but it lacks most of the CLI features so it's limited Solid update. Worth trying once your workflows are already set up 👇show more

I don't think this is anything significant at all,... I think it was just a sound that made for a good ethereal noise when reversed, but when you un-reverse the weird wisp noises in the trailer it sounds like some kind of metal clanking noise. Interesting. #TheAmazingDigitalCircusshow more

Everytime I get into a prime of something, I... just feel like I start burning out of that spark. Like I did this little thing out of passion because I enjoyed doing it a lot more then the brak stuff. 1k still coming don't worry, but this stuff is what I'm thinking I wanna do more.show more

Asked to reflect on navigating a “hellish” public breakup,... Perrie acknowledges that she receives criticism for answering questions about it, “[but] I’m like, ‘But it really affected me massively’”: “People are gonna hate me talking about it… I can’t catch a break. If I talk about this, they’re like: ‘Why are you talking about it?!’ But anyway, shut up! Yeah, [it’s my life]. When you go through heartbreak, it is hellish. You can’t eat, you can’t sleep, you feel horrendous. You don’t feel good enough and you feel like you’ve been left for something better, or whatever it is… Then what makes it even worse is, I feel like the world was then looking at me, laughing at me. I felt embarrassed; I felt horrified. I had serious breakdowns. I did. Because it wasn’t just the heartbreak I was dealing with. I was dealing with everybody looking at me, and I felt ridiculed. I just couldn’t cope with it; I hated it. I was breaking down in performances, which isn’t like me at all. I was crying constantly. I think I was depressed… I know that sounds ridiculous! But I think it was this plus this plus this, and everything on top. It was like, I had to be there for the girls; I had to be switched on; I had to power through for Little Mix – but I also just wanted to be left the fuck alone. But I also was getting followed every two seconds and asked about it 24/7, and it was the headlines, it was everywhere, and it was a lot! And this is the thing – when people are like, ‘Stop talking about it!’ I’m like, ‘But it really affected me massively’.”show more

“i wish i got more laps just to try... things and test the setup in different ways. a lot of what i’ve been doing is just hoping it works. but we’ve done a good job as a team, so i have to be satisfied in the end that i at least got on the track today” 🙃show more

Rosé finds it cute that we can’t pick a... favorite song on rosie, just like her 😭 “Everyone’s like, my favorite is gameboy… no, mine is toxic… no, two years” “It’s kinda cute to see that cause I feel that towards myself too, it feels like they’re all my babies so I can’t pick one but I feel like everyone’s doing that so it’s kinda cute” all the songs on the album are so good, can you blame us 😭😭😭show more

Updated the subagents system in my custom Pi extension... to include: - Pi subagents - Codex subagents - Claude Code subagents The Pi thread can call and spin up any of them, and instead of just using the "codex exec" or whatever, it'll do a tool call that wraps it up in a first class way. Have a decent UI for them already added in as well. Pi being the main thread then having Codex/Claude Code as tools when needed feels so good. A flow I'm already using a ton is: "Implement feature ___, have a cc fable subagent research and plan out the api design + feature, then have a codex subagent implement it, then have a cc fable subagent do a review/fixes focused on simplicity and correctness" I also have a dynamic workflows extension setup and working, but it's not nearly as polished yet. Probably gonna make the subagent system more robust, then built it around that so u could have a workflow that flows between codex/cc/pi...show more

we've shipped an official MCP Server 🚢 I was... a bit skeptical of MCP at the start, but as soon as started using it i changed my mind. It's a lot of fun using tools like Cursor/Claude to build with supabase [details in thread]show more

Elon Musk’s advise how to overcome fear: “Drive overrides... fear. I feel fear quite strongly. But if what I’m doing is important enough, then I just override the fear. So, it’s not as though I don’t feel it - I feel it more strongly than I would like”show more

HTML Artifacts are a big part of how I... work with agents now. Artifacts can be more than just static files. When combined with agents, they can take action or help you take action. This unlocks all kinds of interesting ways to work with agents. This is clearly the future. Check out this writing and scheduler artifact I built in a few minutes. It uses a bit of HTML and JS. All the data is in markdown (Obsidian vaults), so the agent can access and modify it at any time. No DB needed. No sophisticated functionalities. The agent decides all that for me based on the skills, context, and memory it has access to. The best part about this simple stack is that all the important information stays with me. This has allowed me to build a recursive self-improving system and automations that can better tap into coding agents like Codex or Claude Code. I could have paid or built an entire app for scheduling posts, and there are so many of them out there. But I don't need to. I've realized a simple artifact does the job. And the simplicity of it is actually an advantage. Very little maintenance for very high returns on personalization, time, and efficiency. The other benefit of this is that I can add features as I please. That level of personalization feels magical, and we should all be pursuing more of it. All of this just keeps compounding. Of course, this example is just about writing. But I have similar artifacts for research, design, experimentation, evaluation, and so much more. And no, I didn't actually publish the post example I shared in the clip. It was just for demonstration purposes. I actually spend more time than this when writing together with agents. Lastly, having built my own agent orchestrator tool has made me realize that simplifying the tool stack is a superpower. If you are curious about how all this works, I will do a live session next week:show more

I asked our sound designer Gurwal to make this... moment feel like as if a sound recorder on the set would actually be swept away by the flood. As if they wouldn’t be able hold on to the microphone and get the right levels making the sound just barely usable. I wanted it to feel rough, raw and dirty. Initially I thought that this would be loud, but Gurwal suggested instead that the sound should almost dissapear, which I think made the scene way more impactful. I learned a lot by working with Gurwal. Like in this case that less can be more.show more

Napheesa Collier on Olivia Miles’ between the legs no... look pass for a Kayla McBride transition three “That was crazy(smiling), I mean, I haven’t even seen the video yet but just seeing that in real time, it’s like the stuff that Liv can do is just so fun and then Mac knocking it down she was like “that’s more pressure than even a game winner” like you have to hit that. This team is just so fun”show more