๊ณ ์ ๋ ํธ์
๐ง Brant Wedel
9.8K posts
@oli_laban @ibuildthecloud @AnthropicAI @opencode Oh! I see my confusion (I had assumed it was the same as the vscode plugin)
English
@bitbased @ibuildthecloud @AnthropicAI @opencode The Claude Code agent can power the built in AI Assistant. It's got nothing to do with the plugin, which just gives a few useful features for external Claude Code.
English
JetBrains does this, so somehow it's okay for them. I'm not sure why @AnthropicAI is so stupid with it's relationship with @opencode. I really want to know what's the difference is between the two.
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 ๐
English
@theo @node2040 If you have an issue - spawn claude code in a shell and scrape the output instead of the agents sdk (I did this recently - tricky with ink - I just detected prompts/confirmations and showed them as a popup) ... at that point you are just a decorated terminal - no TOS issue ๐คฃ
English
@node2040 This was after it spent 20 minutes reading the code lmao
English
the model that trained on the TOS confirming the TOS compliance of a tool that uses the model.
it's models all the way down.
(opus 4.6 will absolutely say yes to this. it's not lying โ it just has no idea what T3 Code actually does at runtime)
Theo - t3.gg@theo
According to Opus 4.6, T3 Code is compliant with the Anthropic TOS. This should hold up in court right?
English
@DerrickEvans4WV is this a euphemism - just tell us how you really feel about dear leader ๐คฃ
English
๐จ U.S. Marines seen cleaning President Trumpโs Hollywood Walk of Fame star
English
@elonmusk @jonstewart I think literally buying a platform for it makes you the winner on this one bud ๐คฃ
English
Whoever uses AI to write code should be responsible for that code (and liable for any potential consequences).
I don't care what model you used, how you used it, or how much it helped you.
You are responsible for the code.
Santiago@svpino
I didn't know you could disable Claude Code attribution when committing code. To fix it, I asked Claude Code to disable attribution, and it updated the global settings. json file. No more "Co-Authored-By: AI <ai@example.com>" comments.
English
@HarmlessYardDog The same bozos that then decided to go destabilize those regions in particular. ๐
English
Which one of you bozos thought it was a good idea to build the entire world economy off just in time supply chains from the most unstable regions on the planet?
English
@GunloverClub1 those are currently flown by humans - and you can surrender to them - and it is a war crime if the surrender is ignored.
English
Why This Feels Like a War Crime?
In any other era, if you were out of ammo or cornered, there was a slim chance of surrender or a "fair" end. But you can't surrender to a kamikaze drone. It doesn't have a heart, it doesn't take prisoners, and it doesn't understand mercy.
English
@m6502 @Jonathan_Blow Right - not the control system directly (yet) - but for path planning and prediction systems - waymo.com/research/motioโฆ
English
@bitbased @Jonathan_Blow LLMs don't control any car. It's a fundamentally different category of software.
English
Theory:
We don't let LLMs control robots and operate freely in the physical world (yet?) because they'd fall all the time, break everything, and cause massive damage.
But in software the falling and the massive damage are invisible, so it's fine.
x.com/sama/status/20โฆ
Sam Altman@sama
I have so much gratitude to people who wrote extremely complex software character-by-character. It already feels difficult to remember how much effort it really took. Thank you for getting us to this point.
English
@Jonathan_Blow What is a WORD in a programming language ๐ค
English
@TheMG3D They are not integrating ai "into" it - that would be dumb.
English
Why does AI need to be incorporated into a password app?
1Password@1Password
Today weโre introducing 1Passwordยฎ Unified Access. As AI agents start operating inside real production environments, organizations need visibility into how credentials and access are actually used. Unified Access helps security teams discover, secure, and audit access across humans, machines, and AI agents. ๐ More here: bit.ly/4dq2pjO
English
@molecularmusing Programming is a tool to take an idea and achieve the goal of software. I enjoy a code puzzle as much as anyone - but that is not always the goal.
English
I find this extremely worrying, with many of people I respect saying things like "I no longer write code" or "let LLMs do it".
Why did you start programming? Was it never the journey for you, but only the goal?
I genuinely want to understand this, I seem to be the odd one out.
English
@OxfordYazuka @Jonathan_Blow the visibility of the damage is delayed
English
@Jonathan_Blow if the damage is invisible is there damage though
English
'TERRIFYING': Dashcam video shows the moment a Tesla Cybertruck, allegedly operating in self-driving mode, nearly sent a Houston mom and her infant off a bridge before violently crashing into an overpass barrier.
The woman claims she suffered multiple injuries from the incident and is now suing the automaker for $1 million.
English
@elonmusk @IfindRetards You could also say the same thing about white house cabinet meetings
English
@IfindRetards Just a bunch of perverts in a circle jerk
English
I know it's kinda my job to watch things like the Oscars but I refuse. There is only so much retardation one person can take.
English
@jspilman @PAl_l_E @jamonholmgren bang enough sticks together and you get a monkey writing Shakespeare ๐
English
@PAl_l_E @jamonholmgren And that just freakin works?! Like, actually, how and why. We are monkeys banging sticks together!
English
Does anyone actually know how LLMs / agents process screenshots?
I thought they just got a summary from an image classification model, but it seems like they're more sophisticated than that now with multimodal models.
Ryan Florence@ryanflorence
It's weird that I kinda expect agents to be able to read UI code and "see the matrix" instead of the code. But they do so much better at design stuff when you feed them screenshots of their work.
English
@shazcodes The joke is - it doesn't matter - it didn't matter before LLMS, and it definitely doesn't matter after them.
English
@ChShersh Counterpoint: Whoever wrote that enum is an actual hero, and has actually saved lives.
English
I've just seen the 2nd-worst enum in my life
Dmitrii Kovanikov@ChShersh
I've just seen the worst enum in my life
English