rishabh

time to build your own kimi-k2 wrapper with all that data

mdbar.run would appreacite feedback

hi guys made a lil markdown editor that stays in your menubar, still tinkering with it. is opensource

@theo yes

I fly out tomorrow for React Miami. Should I do one last stream today? 👀

@theo W

@aicheye yep!

anyone going?

hmu if your going!

got into @ycombinator SUS 26! excited to learn and build!

@noelthomas30 when it intially came out

@rishabhsaiv When did u apply

who's goin to YC startup school

@saeedsaiyedtwt @theo just go to his twitch and look at videos

@rishabhsaiv @theo stream link

looks like @theo been having a bad day.

@theo thought i missed the stream, went back to find there was no stream and 10k bounty lol

I am not having a good day

@madewithv @theo 3 hours ago

@rishabhsaiv @theo Lol when was this?

ill make a walkthrough soon. Built this after using @FarzaTV's Clicky, loved the idea, but waiting 3 seconds for every response felt unnecessary. So I made an SDK that skips screenshots entirely.

@Chizzydigital @milindlabs @FarzaTV @Microsoft on the website! glance.run the npm packaging is live now. you can ask your agent to set it up there is a prompt on the website.

@milindlabs @rishabhsaiv @FarzaTV @Microsoft Please how can one set this up?

I took Clicky and I made it 5x Faster So I saw that @FarzaTV was using uses Claude's vision to find UI elements on screen, send a screenshot, wait for coordinates back. It works, but it's slow. I replaced that with OmniParser V2 by @Microsoft which is a local Object detection model trained specifically on UI elements. It runs on-device, detects every button, menu, and icon in 400ms, and gives me pixel-precise coordinates. No API call, no latency, no cost. The green highlights you see around the UI elements is the detection overlay and you can see as I am switching the screen it takes no time to detect and highlight which is pretty neat! With Local models improving by the day, Its the right direction for applications like these. Next up: video-synced tutorials where a YouTube tutorial pauses and waits for you to perform each action in the real app. I am not stopping!

@whiteboreds @milindlabs @FarzaTV @Microsoft yes

@rishabhsaiv @milindlabs @FarzaTV @Microsoft does this work with iOS simulator as well?

@theo i just got the robinhood gold card 😭😭

Robinhood spam called me all morning, begging to take the post down. I told them to give me the stock I purchased. “We can’t do that sir” Burn them to the ground. Evil company.

@milindlabs @FarzaTV @Microsoft its actually more usefull for applications than web

@rishabhsaiv @FarzaTV @Microsoft That looks super neat! Is it for web only or works with any application?