I love StarCraft. I started playing it right from the beginning, most of my friends right now are from that era. I literally met people that have spread to almost every continent when I was in my early teens. We played at internet cafes and did not have access to the internet, that was priced differently...
I miss those days so much.
Everybody was from a different background back then, and nobody was anything other than a guy that plays StaCraft at the cybercafe... And now, we are in our 40's and I know Math teachers, history teachers, oil rig operators, software programmers, professional gamers, lawyers and more... hahah So crazy to think about it... and I know them, we talk, what a world.
Oh boy, I've spent more hours playing it than I dare to admit. I won over 10000 battle.net games ... on just one of my several accounts :) When the SC2 beta came out, I played about 50-100 games and never bought the full game, because I knew it would be like heroin to me, and I was already an adult that had to take care of himself.
Even at Burning Man, in the middle of the desert, there is a camp that hosts a StarCraft tournament every year (on the dustiest setups you've ever seen!) :)
My first time playing StarCraft was at summer camp around a decade after it came out.
All the smartest people played it so I wanted to too. Great decision, I have been continually impressed with the people who StarCraft introduced me to.
Back in 2010, during the early days of bwapi, there was a Brood Wars AI tournament held by the Expressive Intelligence Studio at UC Santa Cruz. It's interesting to see how different the approaches were back then, vs this or Deepmind's SC2 work.
A friend of mine created GoBench[1][2] that evaluates LLMs on 9×9 Go using KataGo opponents as Elo anchors, you see real capability differences there, like Astra Max substantially leading all other models. I think strategy is a generally interesting area to evaluate LLMs on
I think we're on the early days of games you connect with your agent to. Human + AI units one versus the other. Like knights with their horses. Not sure which is the horse..
I've been running these with friends recently, it's very fun. I ran irl bot tournaments for board games a couple times but the agent era opens up a huge amount of possibilities.
Must recently I built out a MMORPG puzzle box thing, I wrote a general game architecture doc but left the specific puzzle design up to Fable. Nobody is actively playing rn but I left it up at bot.willmorrison.net.
Did it play by looking at screenshots and sending clicks, or was there other mediation/symbolization?
It sounds like it might have been actually played in real time, which would be very important to distinguish.
I have recently seen other harnesses letting agents play real-time games in what seems like discrete time slices, turning eg Portal into something turn-based https://www.youtube.com/watch?v=ruuGXFAmiOE
Any details about the harness the agents were given? I am curious what representation of the screen and world state was provided to the agents and what tools they had available.
Oh sorry I should be more clear on that. Will add to report.
For agent harness I did Claude Code, Codex, Grok Build. This was primarily a cost driven decision — I have a lot of free tokens and I didn't want to pay API prices for this.
For game harness I used minimal BW-API issue command and get observation apis as tools. I felt this was the most fair way to do it on my small scale.
In the future I would like to integrate code mode and multiple games/I think if it was a best of 5 where each agent could learn from its past games and build its own automations over time that would be much more interesting.
Somewhat related: In 2018, Google DeepMind had already created AIs that were capable of beating professional gamers in StarCraft 2 (the sequel to Brood War): https://www.youtube.com/watch?v=cUTMhmVh1qs
AlphaStar beat one retired professional by cheating.
AlphaStar won a showmatch against TLO, who was never one of the strongest players in the world. He had been retired for over three years by the time of the match. Google set the rule that their system would have human-like mechanics, but it reached upward of 1,500 actions per minute, never issued a wasted action, had a reaction time of single-digit milliseconds, issued commands with perfect accuracy using an API, and could see the entire map at once.
It was later released to the open ladder with more human-level mechanics. Even strong amateurs regularly trounced it. I have beaten it myself. It was strong, but not even close to the level of the strongest human players.
Even the cheater version would have lost handily to Serral or any other world champion.
(It apparently beat MaNa as well as TLO, but those matches were never released to my knowledge. I assume Google cheated even more flagrantly in private than it did in public.)
Starcraft is APM-dependent. Unless the latency will improve greatly in frontier reasoning LLMs (which is unlikely), it will remain a bit like knitting with an excavator.
This is a great idea for a benchmark. Something all the benchmarks seem to be missing is strategy, tactical solutions in most of the benchmarks are all thats required but here requires actual long term thinking and tactical thinking, balancing and orchestration.
Would be interesting if you could team a fast and slow agent together -- slow model can either act directly or maybe just communicate to the fast model.
A ton of conversations about the game must be in the training set. I wonder, is there any way just from watching how they play, of telling if they tend to pick strategies that people complain or meme about online?
I love StarCraft. I started playing it right from the beginning, most of my friends right now are from that era. I literally met people that have spread to almost every continent when I was in my early teens. We played at internet cafes and did not have access to the internet, that was priced differently...
I miss those days so much.
Everybody was from a different background back then, and nobody was anything other than a guy that plays StaCraft at the cybercafe... And now, we are in our 40's and I know Math teachers, history teachers, oil rig operators, software programmers, professional gamers, lawyers and more... hahah So crazy to think about it... and I know them, we talk, what a world.
My first time playing StarCraft was at summer camp around a decade after it came out.
All the smartest people played it so I wanted to too. Great decision, I have been continually impressed with the people who StarCraft introduced me to.
https://web.archive.org/web/20091124210529/http://eis.ucsc.e...
There's a great contemporary Ars Technica piece by a competitor:
https://arstechnica.com/gaming/2011/01/skynet-meets-the-swar...
As an undergrad I did a project using genetic programming. It was not very successful, but it was a lot of fun.
https://tomisin.space/archive/starcraft-genetic-programming/
[1] https://rolandgao.com/blog/gobench/
[2] https://rolandgao.com/gobench.pdf
Must recently I built out a MMORPG puzzle box thing, I wrote a general game architecture doc but left the specific puzzle design up to Fable. Nobody is actively playing rn but I left it up at bot.willmorrison.net.
It sounds like it might have been actually played in real time, which would be very important to distinguish.
I have recently seen other harnesses letting agents play real-time games in what seems like discrete time slices, turning eg Portal into something turn-based https://www.youtube.com/watch?v=ruuGXFAmiOE
For agent harness I did Claude Code, Codex, Grok Build. This was primarily a cost driven decision — I have a lot of free tokens and I didn't want to pay API prices for this.
For game harness I used minimal BW-API issue command and get observation apis as tools. I felt this was the most fair way to do it on my small scale.
In the future I would like to integrate code mode and multiple games/I think if it was a best of 5 where each agent could learn from its past games and build its own automations over time that would be much more interesting.
AlphaStar won a showmatch against TLO, who was never one of the strongest players in the world. He had been retired for over three years by the time of the match. Google set the rule that their system would have human-like mechanics, but it reached upward of 1,500 actions per minute, never issued a wasted action, had a reaction time of single-digit milliseconds, issued commands with perfect accuracy using an API, and could see the entire map at once.
It was later released to the open ladder with more human-level mechanics. Even strong amateurs regularly trounced it. I have beaten it myself. It was strong, but not even close to the level of the strongest human players.
Even the cheater version would have lost handily to Serral or any other world champion.
(It apparently beat MaNa as well as TLO, but those matches were never released to my knowledge. I assume Google cheated even more flagrantly in private than it did in public.)
Marine staggering for example seems like an ideal code mode task.