Jaqb

@benln Gdańsk please 😉

Cafe Cursor in Kraków

@saeed_vz Constantly

Who is doing one prompt with multiple agents at the same time? 😅

@thdxr @realmcore_ There were times new JS framework was announced, nowadays it's "orchestrators". We should have a page with realtime statistics for that and big summary "x days since new orchestrator" or however we name this thingy 😉 btw love all of this and appreciate all of you!

how many times are you guys gonna build this

@DavidKPiano I know it's wrong in many ways, but in corporate env this is more aligned then prototyping. Once again, big fan of fast experimentation

This is what spec-driven development tools/products get wrong IMO: the spec should fall out of the prototype, not the other way around One prototype is worth 100 spec drafts

@connorhpbrn Despite content, why use Dock anyway?! 😉

No one is beating this dock.

@saeed_vz It's my daily driver for a last week and today brought in two new users. Thank you 🙇

Muxy has 1K download a day now 🚀

@neogoose_btw If I can cut off even like 100ms then worth trying. Multiply by 10000 or 100000 - it compounds

@jaqbec it's kinda cool I'll try it but let me know if you need to speedup your file search 😉

I was a user of raycast since 2020 but today I am asking what is going with it and do I even need to keep it installed on my laptop

@ashtonasidhu @bnafOg @RhysSullivan Interesting. Sent a request

@bnafOg @RhysSullivan you have the option for both: - when in worktree mode, each session is its own worktree - when in nonworktree mode, it works on your current branch depending on the task I will toggle worktree mode on and off

has anyone built "the software factory" thing, misc requirements: - able to use my subscriptions (codex / claude) - stacked diffs w/ graphite - able to go from planning -> lots of small tasks - closing the review loop don't love current agent interfaces, want something new

@nbaschez Till today, used raw markdown and nothing else clicked. Let me try ;)

Do you spend a lot of time reviewing markdown docs written by AI? Wish it were a better experience? Say hi if you wanna try a new (free, open source) thing

@mattpocockuk grill-me forever

The top trending repo in the world is mine Madness

@mattpocockuk where you are heading? I've watched your presentations on AI Europe and it opened my eyes. grill-me already is almost a core, cleaned up context from 46k to 21k tokens in Claude when realized how this adds up across hundreds of sessions - almost 9m tokens in March and April! But there's a wall where I can't go below. There's much to consider. I need multiple models from different providers. Already paying Claude, Codex, Cursor and a bit to OpenCode. Utilisation is low on first two. Costs are too much rn. Almost 500$ per month (for me it's a lot). My brain is constantly bombarded with options and I feel I'm stuck. Any advice appreciated. Also will take a chance to ask @0xSero same ;)

I feel sorry for Claude Code I know they're not the one. I'm not overcommitting - not investing too hard I wonder if they know I'm pulling away

@davis7 In @cursor_ai it burnt like 2m tokens in 3 simple prompts - can't afford it. It was low

GPT-5.5 on low reasoning in pi is the most fun I've had with coding agents in a while reminds me a lot of the opus 4.5 release month before the mass lobotomization

@0xSero Never been there for longer then 2 days and each time leaving I'm overwhelmed how busy is it in comparison to Gdańsk/Gdynia/Sopot. But everyone I know from there are very open and friendly 😉

Warsaw is amazing, actually. I hope more people get to visit

@thsottiaux @thsottiaux does same apply to business plans?

Hi! Getting a lot of questions on Pro plan rate limits, so I wanted to clarify a few things: - Your Pro $100 plan includes at least 10x Plus usage, till May 31 with the 2X usage boost. - Your Pro $200 plan includes at least 20x Plus usage, till May 31 with the 2X usage boost. This is also the SAME usage this plan had since the 2x promo in February; we previously didn't document this explicitly. Now to address the confusion. Our pricing page says "5x or 20x usage", and many of you very understandably took it to mean "10x and 40x" given then 2X usage boost. That's our fault. We mixed up two things in a confusing way on that page - (1) sharing that the Pro $100 launched with a 2x boost, making it 10x Plus till May 31 and (2) sharing that Pro $200 retained its 2x boost and sharing for the first time that this equates to 20x Plus. We're going to update our pricing pages to make this clearer. Sorry it wasn't as clear as it should have in the first place.🫥

@aarondfrancis I finally found time to give it a shot to only find out that newest MacOS is causing font issues :/

I'm putting the final touches on the next release of Solo and I've reached a point where it's super hard to develop Solo without using Solo. It holds all my todos and markdown scratchpads. Agents can read / write / comment on all of them via MCP. I'm so freakin pumped

@0xSero The only thing is that when I try it with missions it automatically switch to Droid provided models. Is it known issue or my skill issue?

@0xSero 💡

Do you want to try Droid? I’m doing a giveaway 3 people will win 100M Factory credits each.Thats 5 months of their 20$ a month subscription. Winners selected randomly from comments in 48 hours.

@0xSero @thdxr Not me

Giving away 5 Opencode Go subs Winners selected randomly from comments in 24 hours.

@dSebastien @obsdmd chops.md haven't tried

Now that more and more people are using AI agents, it would be nice if @obsdmd provided a way to show/index/consider content/markdown files in hidden folders (eg .claude/). cfr forum.obsidian.md/t/enable-use-o… I'd personally love to create an Obsidian Base for all my AI skills/agents etc @kepano is this on the horizon somehow?