synergy20

one more reason back to Debian

maybe gtk4 gui first then ask llm to recreate them natively on windows and macos

wow, what about electron.js the bloated cross-desktop GUI, can LLM either totally modernize wxWidgets(to avoid Qt's license mess), or create some light-weight cross platform GUI widgets to make GUI easy on windows/macos/linux that is not resource heavy?

observing changes is slow and very subjective. i ask ai itself to update skill once a while

claudism really sucks, Gemini and codex output so much better, way more like a real human being.

dumb question,why this and even gerrit? github or gitea PR seems much simpler and get the job done well these days

indeed, I'm switching from claude to codex

I wish this can run directly on my RTX 4090, seems like 30B is the sweet spot for dense model to run locally, sadly RTX 5090 is very expensive and I need a new PC and new power supply(and UPS) to run that, adding a second RTX 4090 is another option, but not sure if my PC can do that yet.

i am switching to codex, opus 5 failed me

great for mobile apps, fine for desktops, basically unusable for browsers unless you do wasm, if web can be revamped/improved it can be the best option for cross platform GUI

define criminal activities, is censorship criminal here,are you doing it

true, switched from ollama to llama.cpp these days and it's good. wonder if this is also the best option for edge ai deployment(currently use it on desktop)

all my LLM coding is in go these days

that undercuts their core business, so it will be a defensive play at most to fend off mac and amd's local inference offerings

anecdotal: golang, with c or simplified modern c++

unsloth for small use cases, tinker for enterprise level use cases?

what are those cheap fine-tuning services these days?

    V4L2 (MJPG) -> cap.read() -> CLAHE(night) -> imencode -> _current_frame (web MJPEG)
                              -> resize .25 -> gray -> blur -> absdiff -> contours -> motion?
                              -> motion? VideoWriter.write() : pre_buffer.append(jpeg)
                              -> on stop: ffmpeg remux fps fix -> Telegram/email

a mjpeg system basically, all in python but does need opencv

you probably are overly sensitive and biased, do not forget transformer is the only 'original' for AI so far, the 'original aspirations' nowadays are just incremental improvements. human rights are not rubbish by the way, you might earn high salary now, dare to criticize Mr.Xi at all? you could be in jail and lose everything overnight. without human rights, tech is fragile and mostly harmful in the end.

morningstar said the fair price is $62

it's widespread in rewriting CLI tools, so it's terminal

The "Rust Evangelism Strike Force" is so annoying and it becomes the major reason I don't want to have anything to do with the language, yes I know it's strange.

Almost all HN software related discussion will have some Rust folks saying 'yeah I have a rust project for that', or 'just write this in rust and it will be better', so annoying after seeing those each time, it's like the house-window sales guy keeps knocking my door every day and never goes away.

there are quite a few companies are developing 'proctoring' system to defeat the cheat so you can take self-exam in realtime and everything will be recorded and anything suspicious will be reported, that should be a must-have these days unless something better come out? or current products are not doing their jobs well?

but, it's $160/month(unless you buy a one-year plan that gets cheaper), not too far from $200/month from claude and codex? why should I switch?

or use git-shell so users do not need a full ssh account on the server due to security concerns:

    which git-shell
    sudo echo "/usr/bin/git-shell" >> /etc/shells
    sudo useradd -m -s /usr/bin/git-shell git
    cat my_pub_key.pub >> /home/git/.ssh/authorized_keys
    git clone ssh://git@server/home/git/myrepo.git

hold on, are you saying graphenos has no ads everywhere? I need swap it in then

how is this different from lvgl? is this immediate mode or retained mode?

can vlm be used instead or it's too heavy and slow

still 10x better than the 'finish this leetcode tweak algorithm in 20 minutes and tell me your thought process along the way, and yes you will never need that skill in the real job but we need find out who had time to cram for the algorithm books in the last few months'

It's also 3x slower than opus 4.8 per my use, and 10x slower than codex. Codex can find key design issues in 2 minutes yet Fable is clueless after spinning 20 minutes.