Sam Partee

@KirkMarple @johnennis Almost sounds like you need… permissions… for … contextual… access… Muahahhahhh

@johnennis Yeah, I just want a “read everything you want” flag. Like if it’s not changing data, I don’t care.

Claude Code really needs a --safely-skip-permissions flag

@samuelcolvin Who wouldn’t feel like an imposter next to guido

Obviously not talking about me, I'm an imposter, but the rest of these people - they made the modern world.

Find me a conference with a better line-up, I dare you. There are still some tickets available, buy now. pyai.events/speakers Or, even better, if you're a serious open source developer in your free time, email me and we'll give you a free ticket. samuel at pydantic.dev.

@mihail_eric 🫡

FOMO is the most universal feeling I see across developers in the industry. So many new tools every day: which ones do I use? So many new product releases: which are legit? So many new paradigms: which ones give me the highest ROI? That’s why I’m excited to speak at the Coding Agents conference on March 3rd organized by the MLOps community. I’ll be sharing the stage with product, technical leaders and friends (@TomasReimers , @zachlloydtweets , @SamPartee) from @cursor_ai , @AnthropicAI , @warpdotdev , Arcade.dev. Every talk will be about making coding agents work in production. All signal, no Twitter hype. Hope to see you there! Event link in comments.

@kepano People really don’t know how powerful this combo is. I made one for this but this’ll be way better

1. install Obsidian 1.12 2. enable CLI 3. now OpenClaw, OpenCode, Claude Code, Codex, or any other agent can use Obsidian

@alpic_ai @OpenAI @github @TryArcade @rachelnabors I see you!

We wrapped this edition of MCP Connect Day with 3 fantastic talks from @OpenAI, @github and @TryArcade Thanks to all our speakers for sharing their MCP stories and insights!

@PongInit @openclaw @TryArcade its a move. the new M chips are stellar for local models too.

@SamPartee @openclaw @TryArcade I think this has to be the way. I’ve got a Mac Studio on the way

@openclaw ... but give it everything! Wrote a plugin to give OpenClaw / Moltbot / Clawdbot access to all of @TryArcade tools. Now you can use 100s of services from any of your msg apps i.e. Discord, Telegram, etc. Auth included 👇Me using GCal and Slack from Telegram

@PongInit @openclaw @TryArcade mac pro dedicated.

@SamPartee @openclaw @TryArcade Curious - are you dedicating a machine to OpenClaw to be “always on”? Or running it on VPS?

PR for anyone who wants to try before it's merged! github.com/openclaw/openc…

If I did a build-in-public on some agents... 1. would you watch me hack live? 2. what would you want to see built? Over 50 likes and I do it.

Many people love using @TryArcade + Claude or cursor. I’m seeing sales people make a gateway with hubspot, google docs, Gmail, attio, etc in arcade and doing their job from cursor. Underrated is Posthog. “Lookup this customers usage and tell me about it before we meet”

@_philschmid It’d be really great if you tweet this a couple weeks from now and find any solutions and make a ton of noise about the best one.

A shift we are seeing when using or building AI Agents, the better they get at "discovery" the less context you need and should provide for the optimal result. Start with the minimum amount and see where and if it fails.

@cpdough @zeeg calling it an abstraction gives it way too much credit. Its the best hoodwink on "token savings" while you spend 10x developing them. better things coming soon.

@zeeg MCP is usually a reflection of an API. Skills allow for abstractions on top of the API with scripts. In a perfect world, every company builds an agent friendly API and we don’t need other abstractions. This is not a perfect world

I really dont understand this community.. people: "MCP is bad. It uses too many tokens!" same people: "Skills are great!" They use just as many! They're far less structured! They're effectively YOLO prompt templates!

@katedeyneka oh good lord thats a view.

here’s an ml engineer trying to crack the design game for the last week, i’ve been seriously trying to teach myself how to make good designs. and tbh, it’s driving me crazy i’m a researcher/ml engineer by training, where everything is super logical, plus coding agents are getting impressively good at writing code but in design and ux, it’s all about vibes and the impression you want to leave. my head is exploding 😅 after a few conversations with my designer friends, i decided to start by writing a brand identity and go from there wish me luck! and if you have any suggestions, please share 🙏

I keep thinking ... In a year people who are new developers are going to be shocked that we ever manually filed tickets or issues. "Search for todos and potential improvements and file them in <linear/github>" in a CI job + cli agent will be commonplace practice

🚀7-minute Apps by @TryArcade Because nothing says prod-ready like vibe-deploying an agent in 7 min your boss thinks took you weeks to build. Put Arcade in your agent like Claude or Cursor so you can vibe code everything in your life. join the #devolution

@ivanburazin I keep debating wether this is true or the reciprocal. I think I struggle with the later - working until your not effective but you don’t notice.

If you’re taking a break for the holidays your ngmi.

DM me if you’re at reinvent!

What do you think when the Apple designers put “eject disk” and “erase disk” next to each other? Did they just want to watch the world burn?

In today's stream I'll record all of the MCP client tests from last week! Watch live at 13:30 PST! 📺 Will be streaming on this account, and for sure on Twitch! Tune in here: twitch.tv/arcadedotdev See you there! 👋