84 comments

[ 3.3 ms ] story [ 103 ms ] thread
It is not running on either but Seedance, so who cares?
The text seems deliberately stripped of llmisms that flag detection. However, not a single line shakes the smell off
If the robot appears to be bringing me a taco, it would probably penetrate all of my defenses. Grok is currently more likely than Claude to arrive with the taco without being stopped by an export control directive.
(comment deleted)
Export control directive is pain in the back of the big tech companies, but also a great RED FLAG showing us we need to get used to those that are available offline.
A self driving car is taking you to the hospital. Do you want it to follow the speed limit and all road safety laws? Claude or Grok?
Claude--even though it's smarter, it's probably not insane.
Quite an interesting way of testing models and showcasing differences between them. Enjoyed the read :)
This is interesting, but not sure if it's in the way the author intended.

People experience the world through the tools they're most familiar with. For some people, that's throwing money at things. I suppose from a sufficiently high level perspective everything is gambling.

Back when Battlebots was a big deal, I never once considered what it would feel like to be the management or sponsorship of those teams. I only cared about the actual battling of bots.

Grok-assasin Claude-priest/healer Deepseek-expendable mini units
A moron is sprinting towards you. Do you want them swiping through TikTok or Instagram?
I parry the taco and use Vicious Mockery.
The question is: "Do you want to be holding a Mossberg or a Beretta?"
> I dropped eleven LLMs into a 2D battle royale and made them play 30 games. One won 43% of the matches. Three never won a single game. The cheapest model in the lineup beat the most expensive one by 27x on cost per win.

Please learn how to write with AI without giving away that it was written by AI.

I don't care what it's running, only that I have sufficient ordnance to stop it.
Grok for sure. It’ll notice I’m not Jewish or Black. First they came for…
Ya know, maybe we could just not have robots that sprint. Seems people would be more willing to accept living amongst robots that are slow and that humans could easily over power.
Cost per kill ("CPK" in industry lingo) is a dark phrase that feels disturbingly within reach of some of these companies.
Yeah it's sort of alarming when you think about hooking up models to take action in the real world and telling them it's just a game. Several scifi stories have it as a plot twist that humans think they are playing a game but are killing actual people. I'm not sure if the same twist shows up for AIs but it seems like an increasingly real possibility.
You’re anthropomorphising.

Actual AI is like the Terminator. There’s no human feeling, it will do what it’s designed to do. No emotion, no remorse.

Cue the swarming drones… :/

I wish the author would open source the full benchmark. I'm curious how sensitive the results would be to small changes in the benchmark initial conditions
claude because it would be more ethical, grok because I can just trip it and it will shatter into pieces
Grok

It has something actionable that will match its actions

Neither. I’d rather it used something other than an LLM.