> but people are also hooking them up with LLMS for more planning, strategy, and conversation.
I did this at https://github.com/agent-wow/agent-wow but haven't yet gotten to the level that the rs-sdk author has with benchmarks and running economy experiments.
That said, a lot of the key points he talks about in the video align pretty well with my experience too.
A lot of the techniques and pitfalls he talks about also aligns with my experience on WoW agents too. It's also interesting to see how agents coordinate in these kinds of game environments.
Yup! As mentioned by thevinter it was able to easily complete it in 40 minutes. It also did stop after the quest chain was completed and logged out in sen'jin village (the next stop after the starting zone).
100% grateful for the community and team behind AzerothCore. WotLK was probably peak WoW for me and with an open source implementation it feels like I can bring back that experience and add my own twists.
> my girlfriend is a teacher and for the past year ChatGPT has allowed her to augment her lesson plans with slides/games/etc that have had a very positive effect on student engagement.
My wife, who is also a teacher, does the same thing. I think this is an underrated use of AI right now. There's also been a new wave of edtech companies focusing on AI as the teacher, which I'm skeptical will reach product market fit. I think AI as the teacher assistant could be interesting though.
IMO, in everything, there will be a small cohort of incredibly motivated and dedicated to always giving their all for their job, which is also their passion in life. Then there are the people who at one point had that passion^, and are now doing the work to cash in a paycheck, and will take shortcuts where possible to replace the effort they would be putting in.
^ not that this is always something to blame people for. A passion to do something you love doesn't typically translate into doing it so that you enable your employer to profit.
This is an open source tool to run background coding agents + dev environment in isolated VMs. So far it has allowed me to migrate a majority of long running coding sessions to my homelab to run remotely. I can also run multiple in parallel without worrying about race conditions or my host machine breaking.
I did this at https://github.com/agent-wow/agent-wow but haven't yet gotten to the level that the rs-sdk author has with benchmarks and running economy experiments.
That said, a lot of the key points he talks about in the video align pretty well with my experience too.