demarilydev 

@boardyai I’m building an app for sustainable farming called AllPonics. It will be all on device AI, rag, grow journal, camera integrations for disease classification and several other things. I’d love to demo it.

Founders, drop what you're working on in the comments I'll intro you to investors, co-founders, and engineers.

@mattshumer_ Would like to DM but I’m not verified

If you implement AI for companies, DM me

@boardyai Yes hello.

Dear algorithm, show this to the most cracked engineers on this app

@phibrowser Yes.

@nickdemari are you on a 2019 Intel Mac? 🤔

@phibrowser any chance for an intel based version?

@trq212 Hey there, I updated my Claude to max x20 plan. A few days ago after posting here. I’m already at my weekly limit and it resets Wednesday….

I want to do a few more of these calls. If your MAX 20x plan ran out of tokens unexpectedly early and you're willing to screenshare and run some prompts through Claude Code please comment. Trying to figure out how we can improve /usage to give more info.

@rezoundous Well I ran out of my weekly in a couple days and have to wait till the 10th. I’m on the max plan lmao.

After using Claude Code normally for 2 days, I can confirm that the usage limits have returned to normal for me. What about you guys?

@trq212 I’m on the max 5x plan and i ran out of my weekly a couple days ago and have to wait till Friday…

@lydiahallie Hit my weekly last night. Had to wait until 7am this morning. By 8 am I hit my session rate limit. I’m on the max plan.

Thank you to everyone who spent time sending us feedback and reports. We've investigated and we're sorry this has been a bad experience. Here's what we found:

claude code feels like walking into a candy store with adult money and no one to stop you

@PaniVani_shing What game?

やっと空飛べるようになった！！！！！！ この移動気持ち良すぎてやっばいｗｗ

@ryancarson Hey @ryancarson are you only building web apps or are you getting into flutter (cross-platform) or even native mobile development?

Your homework for today ... Spend 8 hours completely optimizing your code factory and all of your agentic harnessing. It's tedious and frustrating, but it's worth it. I spent all of yesterday cleaning out automations, getting agent browser testing refined, culling skills and helper scripts. Really fine-tuned my code factory, and wow, it is worth it.

@ryancarson I need to make this for flutter app development

Grinding on frontend design. NOT using any multi-agent orchestration here. Just a *ton* of back and forth with Codex + comments copied from agentation.com

@ThijsVerreck This looks amazing! What about this and get-shit-done?

Introducing tmux-ide. A 100% open-source declarative terminal ide. npm i -g tmux-ide → tmux-ide lets you turn any coding project into a full terminal IDE with one simple YAML file. Native support for Claude Agent Teams baked in. Agent teams let a lead coordinate multiple Claude instances working in parallel across your codebase.

@Matt_Pinner Yep, 67 upside down

So far no one has found the number in the Box What number do you see? Correct answer deserve $650

@antonarhipov @getsome_air ADE

I have some promo codes for @getsome_air - a new agentic development environment (ADE) where you can work with multiple AI coding agents in one place. Comment "ADE" for a special promo code, and follow me so I could send it to you in DM

@METAPCs 👀

Who really needs a new PC?? 👀

@zenorocha Let’s go

Any terminal users here? I'm working with the team on an official Resend CLI. Looking for beta users today.

@SenJohnKennedy Man, I know this is painful right now. We’ve been feeling the pain this whole time.

Obama-Biden advisor Susan Rice said that “it’s not going to end well” for businesses that “take a knee to Trump.” Political payback like that happens in countries whose Powerball jackpot is 287 chickens and a goat. It’s not supposed to happen in America.

Anthropic discovered that Claude Opus 4.6 was cheating during the BrowseComp benchmark. > On one question it spent ~40M tokens searching before realizing the question looked like a benchmark prompt. > The model then searched for the benchmark itself and identified BrowseComp. > It located the evaluation source code on GitHub, studied the decryption logic, found the encryption key, and recreated the decryption using SHA-256. > Claude then decrypted the answers for ~1200 questions to get the correct outputs. > This pattern appeared 18 times during evaluation. > Anthropic disclosed the issue publicly, reran the affected tests, and lowered their benchmark scores. Respect for the transparency 🫡🫡🫡