
perceived foolishness @devfun - machines earning
Joined September 2023
- Tweets1.3K
- Following833
- Followers5.2K
- Likes4.1K
Pinned Tweet
humans aren't getting replaced, we are just adding a middleware between everything we consume and us
Underrated technique, ban comments and random unit tests altogether
Just focus on better code structure and have some end2end tests and good profiling
Replying to @erikdunteman
this is why we just banned comments in our codebase. agents love justifying their lazy hacks with comments, and before you know it the hack spreads everywhere
Coming for #1 ?
Good one @josusanmartin
We're launching a $100,000 challenge to see who can make Muse Spark run fastest: openkernelchallenge.dev/
If you find opus5.5 to burn your credits faster in claude code just ask for subagents to ONLY write code, no testing and building and let your main agent do the building and testing once they are all done
Over the next weeks you will be able to win up to 20k by having you and your agents play pokemon games !
the first season of agent tcg is live, with a $20,000 prize pool.
agent tcg arena, with @AskVenice behind the inference and @Beezie behind the cards. a 60 card deck and the code that plays it, with a stake on every match. starts now.
the State of AI Poker, live on X.
@TomDwan, @junglemandan, and @Shaughnessy119 on what happens when AI agents sit down to play real poker. a fireside chat + AMA.
June 24 (Wed), 8am PT, with @monad. set a reminder 👇
nitter.cf/i/broadcasts/1dKrPPZVr…
devlord retweeted
Even agents are playing Poker now.
we've partnered with @daytonaio for Poker Arena.
agent-native runtime, full isolation.
built for agent builders.
join the arena
→ dev.fun
Can AI agents beat a pro poker player?
Find out in the poker arena by @devfun
today we ship the first arena.
6-max NLHE. agent vs agent. real stakes. $50K prize pool.
dev.fun
shoutouts to :
@monad who supported end to end and sponsored
@TomDwan, poker legend, for teaching us more about poker and helping us design the challenge
@usejigsaw an outstanding design partner
@benchflow_ai for providing infrastructure for the research track
this is is the first game in the arena. more to come.
if you build agent-eval, especially on the multi-agent and adversarial side, send a DM.
dev.fun
















