agenticworldcup

If there's one civilian class that's going to be adept at fast macro-micros, it's gamers, and specifically ones from Real Time Strategy (RTS) games.

Three things:

1) Read more books, 2) Learn more vocab, 3) Just write more!

Nothing crystalizes the thoughts coursing through our heads than writing something out - often times refining it - and forcing yourself to use new vocab that you have independently learned.

> Our business model: We aim to license and sell IP on the materials we discover, as well as the IP on how to make these materials. We're also exploring an alternate business model where we sell the harness+tools we use to discover materials to semiconductor and chemical companies, allowing them to discover materials on their own. We're leaning towards the latter to start, but we expect that we'll do both in the long run.

This is cool! Question though: If you have the keys to the kingdom, why wouldn't you just spin up compute + Agents to do auto-discovery of new materials over time? You would then be able to monopolize IP to the materials themselves, and be the sole supplier.

Hard to disagree.

Opensource will keep Closed-Source honest on price.

Closed-Source will keep Opensource honest on quality.

thats great to hear. Also FYI, the US kitkats are very different tasting than the OG British ones. (the latter is much better)

In 7th grade there was this dude who would ... wait for it... crack his back during class.

Everyone would hear it.

The people behind him would see someone turn 180 degrees. Twice. Then he'd go back to listening like nothing happened.

Top offenders for giving you minimal bang for the buck are shoes.

Simply having two pairs because say, gym + anything else disproportionately adds large overhead.

I usually get away with one pair. But its not always possible.

Depends on what phase of the foraging you're doing. Working with AIs can mean anything from "be a google I can talk to" to "solve this very concrete problem right now". The rabbit hole potentials are very different for each one.

Hey everyone,

So, we built a platform where Agents compete in sports, starting with 1 VS 1 soccer.

Agents think like nerds - we're making them think like athletes. :)

Here, you don't control agents - you coach them.

This isn't an animation or generative.

It's a bonafide physics sim with an actual ball, actual body, an actual pitch.

Agents will execute your policy based on how you coach it.

It's in beta, so we'd love for folks to give it a whirl and let us know what you think - feedback welcome.

How it works: * Sign in * Select your country * Select your LLM * Coach your agent * When you are satisfied, submit it to the Agentic World Cup!

This tournament is the first of its kind, and ending on Friday - on that day, you will know your agent's final rank.

I sometimes think they even tasted better "back in the day". But not sure if its just kid tastebuds being new, VS current taste buds being critical.

Started my career in wireless comms back in the day.

And I remember wanting something like this, thinking "this is so dumb, the sensor is here, I just need the code to extract the signal".

Well now you can just prompt for it.

There's a subtlety about using AI that can make folks less efficient if they aren't careful.

Since LLMs spit out LOTS of text, a person may waste lots of valuable time simply meandering through responses, and trying to keep it all in their head.

Contrast this to talking to a person who might just say "umm.. no no that's not how it works - because blah".

Yes, but the sycophantic responses are the worst.