Presenting Mixture of Tunable Experts (MoTE): Behavior Modification of DeepSeek-R1 at Inference Time - a method extending the MoE architecture of LLMs. By tuning 10 key experts, it enables meaningful and focused behavior changes on-the-fly. Mon 18h CET: https://t.co/5cFW6dkZ9X
Annoyed by unhygienic #feedback buttons? We provide a contactless and entertaining way to collect feedback! Get in touch with us.
https://t.co/3V9rBw9IE6 #COVID19
We are happy to announce our first meeting on Thursday, May 3rd at @check24de in Augsburg with talks from @MathiasBurger on advanced Composer usage and from Benjamin Pflueg on how getting hooks in your git automation. More infos on our @Meetup site https://t.co/UXpI8yfYf6
Don't miss our next @phpugmunich meetup on Wed, 28th of March at Chip with the following cool talks: "Developing in Symfony 4" & "The Myth of Untestable Code". We'll also raffle off some @jetbrains licenses.