Загрузка видео...

Не удалось загрузить видео

На главную

UPDATE: Ended up with this cool little tool to both build and verify the training data quality; it turned out very accurate! So I am at least happy about that (tho it obvisouly was the easy part) The pipeline to produce this kind of training data (from any Warsh...

38,057 просмотров • 6 месяцев назад •via X (Twitter)

Комментарии: 0

Нет доступных комментариев

Здесь появятся комментарии из оригинального поста

Похожие видео

I tried to tell y’all how it works when I’m on the beach or in a tourists trap. I see these guys walking around with icy drinks and since everything else in the country was cheaper than they are here I would assume his drinks would be too. These guys will come by and even take your “order” if I don’t see something I want, he will say he can make it for me. These women fell for this and ordered 3 drinks from him. One of the ladies was so thirsty she immediately started drinking it until he told them they owed him $75. Mind you these are adult drinks, the cups look to be a decent size so is it worth it or are they just tripping out? I am on the fence with this one, if it’s clean and good quality, I may say this is a fair price but the only one I’m questioning is the one who tried to give it back after she already drank out of it. Rarely will I side with a street merchant because I feel like they’ve ripped me off quite a few times. But I think his price is valid for this. I’ve paid close to the same price for much less when I was at the beach. Most of the time I can tell they are well drinks that they tell me are too shelf. Many people can’t tell the difference but I can. I only drink certain brands and I am very used to what they taste like. This kind of interaction is why I now only buy from restaurants and bars like I mentioned before. I am not going to get into an argument with someone over something I ordered but failed to check the price first. That old saying, “if you have to ask them you can’t afford it.” That doesn’t apply here because if I have to ask then it means they should have listed the price up front.

SonnyBoy🇺🇸

289,793 просмотров • 2 месяцев назад

The number one question I get in the Claude Code / Cowork Community: "how do I share my Cowork skills with my team?" Here's the problem. You build a great skill. You zip it up. You drop it in Slack. Your teammate downloads it, uploads it, and maybe it works. Maybe they upload it wrong. Maybe you update the skill next week and nobody gets the new version. You're now maintaining skills through chat messages and hoping for the best. That doesn't scale. I just put out a video breaking down the three methods I've tested for sharing skills and plugins across a team. From dead simple to fully synced. Method 1: Shared drive (Google Drive, SharePoint, etc). You put your skill files in a shared folder. Teammates download and upload them into Cowork. It works, but updates are manual and there's no version control. Method 2: Built-in sharing on Team and Enterprise plans. You can share any skill directly with a colleague or publish it to your org directory. When you update the skill, everyone gets the update automatically. This is the easiest path if you're on a paid plan. The catch: there's no approval workflow for org-wide sharing, so set a clear owner. Method 3: GitHub repo. This is what I use. Your entire Cowork workspace -- skills, plugins, claude.md, folder structure, project files -- lives in a private repo. Teammates clone it. When you push an update, they pull it. Everyone stays in sync. You get version history, access control, and a single source of truth. The GitHub method sounds technical, but it's really just two steps: clone the repo, point Cowork at the folder. I walk through the whole thing in the video, including how to use .gitignore to keep personal files (like your morning briefing) out of the shared repo. This works for Cowork, Claude Code, and Open Codex. The infrastructure is the same. Full video linked below. If you've found a different approach that works for your team, I want to hear about it. Comment or reply and let's figure out the best practices together.

JJ Englert

16,176 просмотров • 4 месяцев назад

Scottie Scheffler says they didn’t find his ball on 17 and he actually asked people to stop searching for it: “The rules official said it landed just barely left of the grandstand thing. I don't know what you call that, like a sponsor area or something. And Teddy had a beat right on where it was coming down. So when we get up there, it's past the fence that marks the TIO, so he said anything that's in there is it part of the TIO. So then we said -- we tried to figure it out. I said, if I find it, does that help me; can I drop it -- since that would be about 50 yards closer to the hole. He said, yes, you can then use that spot, but you might have to go to the other side of the TIO, which I didn't know exactly where that would be, and that's not a great angle coming across there. “So decided to stop the search and go back and drop it doing point-of-entry TIO relief. Actually I did that once this year during the Byron as well. Not something I'm proud of but I was familiar with.” He went on to say: “I stopped them. They had guys pointing from up there, like it landed right here, and I just kind of hauled up there, and I was like, guys, get out of there, stop, do not find the ball. Fortunately it was my security guy that I've had for a few years here. His name is Brucey. And then Woody was up there as well. So both those guys are pretty -- I know them quite well, so when I said, please don't look for the ball, they got out of there.” The Open

Flushing It

1,780,460 просмотров • 1 месяц назад

mark explained the confidence behind his big decision “that kind of thing felt so precious. i mean, even putting aside security, money, all these things.. the fact that i still had something i wanted to achieve. that felt so precious. ive always wanted to do things well, to really reach the top in everything. as someone who wakes up every day with this drive to live at my best, i began to wonder, “what does ‘the best’ actually mean? and whats my ultimate dream? what is the greatest thing i can leave behind in this life, in this world?” so everything started connecting. and if this is the greatest dream i believe in, then i needed to commit to it with my absolute best effort. honestly, everyone in this world is living by their own standards and who you are depends on, the standards you live by. but honestly, ive always had a bit of a loser mindset, what a man should be? and i never felt like that matched who i am. ive always had a complex about that, like rough or edgy and not too exemplary either. but suddenly i got confused about all that. i ended up talking about it to david, david kept asking me “what is that coolness you have in your head?” that made me dig deep and really think. i realized i should actually live by what’s ‘good’ and i need to express that through music. so i found this dream of showing ‘goodness’, i want to show the world what real goodness is and making music like that. ultimately, for the next generation.. i really want to show the next generation what that is. so my dream became very clear. you can be good and also be cool, i want to create a new kind of cool. i truly want that and i want to live it and achieve it in my own life. i realized this is truly something worth dedicating your life to.”

ٰ

32,996 просмотров • 18 дней назад

acpx v0.4 ships Agentic Workflows, or as I like to call them "Agentic Graphs" It let's you create node-based workflows on top of ACP (Agent Client Protocol), to drive any coding agent (Codex, Claude Code, pi) through deterministic steps This let's you automate routine, mechanical legwork like triaging incoming PRs, bugs in error reporting, and so on... For example, OpenClaw receives 300~500 new PRs per day. A lot of them are low quality, but they still relate to real issues, so you have to address them somehow You need to: - extract the intent - cluster them based on intent - figure out if the proposed changes are legit, or whether they are slop local solutions, like trying to catch flies instead of drying out the swamp - if the PR is too low quality or the intent is not clear, close them - run AI review on them them and address any issues that come up - refactor them if the changes are half-baked - resolve conflicts - and so on... So that when the PR is presented to the attention of the maintainer, all the routine legwork is done and the only remaining thing is the decision to (a) merge, (b) give feedback to the PR author, or (c) take over the PR work yourself I wanted to build this feature since a couple months now, since Codex got so good. OpenAI models are now good at judging implementation quality, so I found myself repeating the same steps I wrote above over and over I also tried putting all this in a single prompt. But I believe there are workflows that should not be a single prompt, but a sequence of prompts in the same session That is because like humans, LLMs are prone to PRIMING. I claim that putting all steps in the same prompt at the beginning of the context will generally give suboptimal results, compared to revealing the intention to the model step by step Creating such a workflow also gives more OBSERVABILITY into the each step that an agent is supposed to take. Agent generates JSON at the end of each step, and that structured data can be used to monitor thousands of agents running at the same time in an easier way, on a dashboard Similar features have been introduced in e.g. n8n, langflow. But AFAIK they are not integrating ACP like the way I do I wanted to have a fresh approach, and to build an API that I can develop freely the way I want, so I created a new workflow API inside acpx The video is from the workflow run viewer, but that is not where you build the workflow. You build it by using the acpx flow typescript API. See examples/pr-triage in acpx repo Before building that, I started from a Markdown file with a Mermaid chart of the flow I had in mind. The Markdown file acts as a spec for the flow, and I have built the workflow through trial and error. I call this process "workflow tuning" I started working on acpx repo PRs one by one, tuning the flow, slowly scaling to more PRs. Finally, when I felt confident, I ran it in parallel over all external open PRs in the acpx repo. I believe it already saved me hours this week My next goal, if well received, is to set this up on a cloud agent so that it can process the 300~500 PRs the OpenClaw repo receives every day, in real time, as they come in I believe this will save all open source maintainers around the world countless hours and make it much easier to herd and absorb external contributions from everyone!

Onur Solmaz

149,558 просмотров • 5 месяцев назад