@revengeday wenn’s denn mal so einfach währe… statdessen nasenklammer auf und rumschrauben. Was hab ich da ne Lust drauf, aber der olle Flachspüler muss einfach raus…
dunkelstern@corteximplant.com
Posts
-
New toilet acquired… now i have to install it… dang -
New toilet acquired… now i have to install it… dang@revengeday package conflict: old toilet is installed
-
New toilet acquired… now i have to install it… dangNew toilet acquired… now i have to install it… dang
-
Meine Allergie und meine Finger bedanken sich.@revengeday die katzen knistern beim kämmen
-
Meine Allergie und meine Finger bedanken sich.Meine Allergie und meine Finger bedanken sich. Wurde heute schon 4 mal gezapped. Könnte es vielleicht mal regnen?
15% Luftfeuchte? Argh…
-
Chooms, I found an old project file and finally completed it.@revengeday @kaiserkiwi there's just one issue really i think: Sometimes while tapping it tries to select something and pops up the copy menu of the Os. That's a 100% combo breaker
but it really works nicely until the phone decides to throttle (i doubt you can do anything about that) -
Chooms, I found an old project file and finally completed it.@revengeday error phone overheated at level12… yes really, started to stutter badly

-
gemma 4 e4b isn't half shabby, but i didn't think it would run in llama.cpp-vulkan in ubuntu on this lenovo yoga laptop with an AMD Radeon 860M GPU.@lritter that’s absolutely the same thing i am feeling on this. I have been tasked at work to build a copilot/teams “Agent”. The official SDK from microsoft is version “alpha 50”, documentation is completely wrong and the “usecase” is built on hope and prayer and does not work in 60% of all cases. Copilot apparently does so much “Reasoning” in the background it burns through the token context window in no time and then starts to do weird things. Tool calls work in 80% of the cases but in the 20% they do not work it does hilarious things and wrecks the workflow completely. Doesn’t help that copilot has at least 4 ways to build “Agents” where 1 is basically just a prompt, 1 does not work and 2 need copilot pro subscriptions and ms developer accounts which cost you an arm and a leg.
I completely do not understand why anyone wants to use this or how this should replace workers…
-
gemma 4 e4b isn't half shabby, but i didn't think it would run in llama.cpp-vulkan in ubuntu on this lenovo yoga laptop with an AMD Radeon 860M GPU.@lritter i am with you with executing or modifying stuff but tool calling for RAG/information retrieval is useful in my opinion. I mean if you have a choice of actually getting valid information via tool call or hallucination i select tool call. Another valid option is context exhaustion, save some summary to a memory file and retrieve it if you exhaust your context window. Agentic behaviour is just marketing BS, cannot really work in my opinion because it is not intelligent, just fancy text completion…
-
Cute date idea: burn down Sam Altman’s house 🌸@revengeday chances are you’re meeting your significant other while trying, doesn’t even need a date, you’ll just meet someone
-
gemma 4 e4b isn't half shabby, but i didn't think it would run in llama.cpp-vulkan in ubuntu on this lenovo yoga laptop with an AMD Radeon 860M GPU.@lritter try quantizing the kv cache to Q_8 as well, you should be able to reach 22 tokens/second. Sadly the edge models are really bad with tool calling (they often like to hallucinate instead of actually calling the tools, seems to work better with XML tool definitions instead of JSON but YMMV) but the MoE models that are coming out lastly are really fast in comparison.