Nvidia RTX 1070 and Gemma 4 E4B. I did not expect ths to work as well as it does. The answers are fast and surprisingly good for such a small model. The Setup with ollama and OpenWebUI took minutes.
This is a 10 year old GPU. Really hope #OpenSource will win in the end.
Entropy requires garbage collection. AI code replicates patterns including bad ones. You need periodic clean up of your documentation and code, or your codebase drifts into chaos.
@dhh Dude, your media literacy is going down the garbage collector. First, you repost Bryan Lunduke, who became basically a right wing propagandist. Now you repost straight up propaganda accounts.
@dhh Is that just a gut feeling or did you ever read the research on misinformation? Please stick to web dev content. You are making a fool out of yourself.
@dhh@skovalyov The two guys you mention in your post Trump and Musk are full of identity politics. "America first" -> Identity politics... They deal is the friend/enemy dichotomy. Is that better than oppressor/opressed?!
@dhh If you believe that "freedom of speech" bs of Musk, you are not as smart as I thought you are. Musk is actually just a oligarch now... and oligarchs are known for thing it is "freedom of speech" right?!
@dhh I started following you a year ago, as an aspiring web developer, because I thought you are a reflective and critical thinker. But now you start going down the Joe Rogan - Elon Musk bullshit train, and I do not think I am following you there. Sorry to see...
Same. Best point he makes is: Often times (for example in automated testing) we don't want faster results, but better results, and #AI is not able to give us better results at the moment.
https://t.co/wfgxG1alJU
i'm convinced some people go into programming to express things (à la art), to discover things (à la science), or to solve things (à la engineering), and these are the roots of philosophical divides between languages, priorities, working relationships, and value judgments
"That's what so many programmers have a difficult time internalizing. They are in effect very expensive biological computing cores, and the real scarce resource. Silicon computing cores are far more plentiful, and their cost keeps going down." https://t.co/sk1k2eucNV
"and estimating large projects is virtually impossible. Yet the industry keeps insisting that the method that hasn't worked for sixty years will definitely work on this next project, if we all just try a little harder. It's the definition of delusional." 2/2
@dhh speaking truth as always: "Since the dawn of computing, humans have sought to estimate how long it takes to build software, and for just as long, they've consistently failed. Estimating even medium-sized projects is devilishly difficult, ..." 1/2
https://t.co/76AzMOL31E
The web is full of #DarkPatterns that companies use in their design. I found this site that collects them and gives some examples for each.
https://t.co/XphIlKrmw2