Sabitlenmiş Tweet
Theo - t3.gg
59.6K posts

Theo - t3.gg
@theo
Full time CEO @t3dotchat. Part time YouTuber, investor, and developer
San Francisco, CA Katılım Ekim 2016
4K Takip Edilen302.1K Takipçiler

@theo I mean, falls into the same camp as Conductor and Commander, right?
should be ok
English

They’re trying to community note my product drop 💀

Theo - t3.gg@theo
T3 Code now supports Claude. If you have the Claude Code CLI installed and signed in, you can use it with T3 Code. Hopefully the lawyers won't make us remove this 🙃
English

@theo did anthropic give t3 code approval or are we just flipping the dice and hoping for the best lol
English

@RaillyHugo @camilocbarrera @cuevaio @Cloudflare @linear @xata @kapso_ai @polar_sh @meilisearch @pagerduty @DrizzleORM Interesting! What can we do better?
English

@camilocbarrera @cuevaio <75/100, Room to grow
@Cloudflare (71)
@linear (70)
@xata (70)
@kapso_ai (67)
@polar_sh (67)
@meilisearch (67)
@PagerDuty (65)
@DrizzleORM (55)
uploadthing by @theo (37)
English

@theo you're just using the tool fundamentally wrong. any ai coder/llm gets linearly worse with how big a task you give it.
And the smaller the task, the more accurate and powerful it becomes. If your AI is working on anything longer than 10-15 mins the problem is you not the ai.
English

@jetpackjoe_ We do much less customization than Conductor
We’re also open source which I think brings more scrutiny
English

Who’s got a polymarket on time till we get a legal notice?
Theo - t3.gg@theo
T3 Code now supports Claude. If you have the Claude Code CLI installed and signed in, you can use it with T3 Code. Hopefully the lawyers won't make us remove this 🙃
English

@log1400 It works but the alert shows up still? Clone the repo and see if you can fix it
English

@theo Nice, I see cursor on the list, would be nice to get out of the editor and still have composer 😎
English

@theo I was wondering if you got permission or not.
I'm putting money on: they're going to be dicks about it.
English

if you are not using the compound engineering skills, you are missing out on an exceptionnaly systematic workflow.
You should always start a session in /ce:brainstorm then /ce:plan then you need to do /deepen_plan which will infinitely help, deepen, and find issues, then do A FEW passes of /ce:review that will spawn several sub agents to review your plan. (I sometimes do 2-3 pass)
Then only, /ce:work, and finally again, 2-3 pass of /ce:review
Then I can call that PR mergeable.
It sometimes takes 2-3 hours but that's how you properly work, the quality of my features and absence of bug in the end has not been comparable to just "Starting in plan mode" By @bcherny which probably is the reason why claude code cli, app, and other stuff is such a shitshow of lags, memory leaks, etc flickerings.
github.com/EveryInc/compo…
English

@devipt97 u g h
@jullerino we should remove anything "ultrathink" specific, anthropic gutted all of this awhile back
English

@theo When enabling Ultrathink, the UI does not update to that, the also the options still show whatever was last selected (low/medium/high), After entering the UltraThink selection becomes unresponsive, until manually deleting Ultrathink text for text box

English

@saltjsx @complex_maths *as far as we understand*, this shouldn't violate TOS. Sadly they have been entirely unwilling to clarify.
English











