I don't really work on L2j anymore, but from time to time, I check up the forums just in case someone built something cool, and I stumbled upon this:
It's actually really easy to implement LLMs (both local, like gpt-oss, and online, like ChatGPT or Gemini) for any sort of action in L2.
Even without training a model explicitly, a good GPU and some basic LLM knowledge can take you very far.
Here is an example of an auto play bot I made in 10 minutes that uses gpt-oss (which is mega overkill) locally with a 5090 to do some basic farming.
As you can see from the LM Studio responses, it is fairly fast (and uses reasoning too) to think about what's the best course of action for a given situation.
Basically just a quick proof of concept. If I had time, I would make something like this for auto-play/farm or bots, since LLMs would play really nicely with fake players that can actually think and are not completely pre-programmed. It's quite cool.
----------2025----------
TheDarknessFear promoted to Gaming Moderator. Reason: Very active and helpful. (3 September 2025)
Atom promoted to Gaming Moderator. Reason: Promotion by Maxtor. (3 September 2025)
Question
DVL-Java
# Automatic Vote Reward System
VoteRewardSystem= True
VotesRequiredForReward = 5
VotesSystemInitialDelay= 10000
VotesSystemStepDelay= 100000
VotesRewards= 813,5;
#Leave empty to disable one site
#if you need just one of these
VotesSiteHopZoneUrl=http://l2.hopzone.net/vote.php?site=77566
VotesSiteTopZoneUrl=
ServerWebSite= site server
etc to exw kai den votari kai kala sto game lei egine vote ala stin pragmatikotita den exi gini kai sto game server dixni
an mpori kapios na me help gt malon kati exw kani la8os.... to pack m ine l2jfrozen
[AutoVoteReward] Server HOPZONE Votes: 0
4 answers to this question
Recommended Posts