aurbano

For sure!

I’m approaching it as a simulator core that provides a bunch of entities and primitives, that then couples with plugins providing simulation layers, all of which are optional or changeable

So should be trivial layer to adjust any part or provide simple/complex versions or whatever!

And thank you for the feedback! Did you publish your simulator anywhere?

That’s exactly what I’ve been doing, and so far so good!

Haha well, as much as I’d love making this by hand I don’t have the time - so this way I get to focus on gameplay and simulator mechanics!

What a coincidence! I had been thinking of trying to make my own version of a city builder game (like sim city or cities skylines) for years and finally started last week - using rust and Bevy for the simulator

I’m trying to make the most realistic city simulator I can, using published papers on economy models, welfare, immigration, social policies… to drive each aspect of the simulation - and then use it to drive the game

So far I’ve used a team of agents to build the firsg phases of the simulator, and it’s looking really promising!

It’s my first time making such a complex game, but I’m super excited to see where it goes :)

Not much to add, but as a very happy uPlot user here - just wanted to say thank you for such an amazing library!!

This is awesome!

Would it be possible to ditch Twilio and build it as a peer-to-peer system though? Or does that always require a coordination server?

My point was that instead of blaming ML - or optimisation tools really - for gaming objective functions and coming up with non-solutions that do maximise reward, AI could instead be used to measure the reward/fitness of the solution.

So to the OP's example "optimise a bike wheel", technically an AI should be able to understand whether a proposed wheel is good or not, in a similar way to a human.

Is AI the danger, or is our inability to simplify a problem down to an objective function the problem?

If anything, AI could help by "understanding" the real objective, so we don't have to code these simplified goals that ML models end up gaming no?

2kW is literally the output of my patio heater haha

This is awesome! It makes reading the articles a lot more engaging as I can directly see comments without the back and forth :)

I might start reading the actual submissions more often instead of just the comments

That's a great observation actually! They should've made the design do that automatically based on story ranking

I see a lot of comments wondering how AI could be useful as a software engineer so I'll give my take on it:

I envision it being able to fully replace a junior engineer, and in some use-cases senior engineers as well.

In the case of junior engineers: the AI should have access to an internal knowledge base (i.e. Confluence) and the task/ticketing system (Jira), and ideally the internal chat (Slack). I would assign tickets to it, and I'd expect the AI to reply with comments asking for clarification when there is something unclear, or proposing an implementation before starting if it's not a very simple task (this could even be defined in the task, using story points for instance.

Once cleared, the AI submits a PR linked to the task - so far just like any engineer in the team would. The PR gets reviewed as usual, with suggestions/requests for changes made by the (human) team, which then get addressed by the AI. With the big difference that all this process may happen in less than 1h from ticket creation to PR review.

I wouldn't expect it to be able to implement complex features, onboard new libraries, or rearchitect the system in major ways to accommodate future features - just like I wouldn't expect that from junior team members.

It would obviously be amazing if it could incorporate previous PR comments into it's "context" for future work, so it could learn and improve.

Separately I mentioned it could also do part of the job of senior team members - in the form of PR reviews. If it has access to every previous PR review and learns from them it might be able to give insightful suggestions, and for very large codebases it could have an advantage over humans as it could find patterns or existing code that may be overlooked (i.e. "It looks like this util function you added is the same as this one that was already there", or "This code looks different to similar areas, but follows a different pattern, you might want to rewrite it this way //..."

Is GPT-4 there? Definitely not, perhaps an LLM is not even the way to achieve this, but I absolutely see this becoming an incredible asset to a tech team.