I can't seem to find how to configure it with Ollama and a locally installed LLM. Can you please someone help me out with that? @Steve8708 ?
@zeteya2 күн бұрын
I believe that Qwik already compiles to HTML output using SSR, what is the advantage of integrating with Astro? Can you not achieve the same performance with Qwik alone?
@simbalarue04 күн бұрын
Hi, in the meantime congratulations for the video, I wanted to ask you some questions for a project that I would like to realize. 1) I would like to create an AI always with python, but customize it, give it a name for example, 2) How could I make sure that he remembers the information I give him? For example, that they remember my name or my date of birth? 3) All this of course I would like to pass in a text to talk to talk to him, and turn him into a friend, Thank you in advance if you will answer me :)
@dkazmer24 күн бұрын
So is it better to hydrate or to dry?
@IStMl4 күн бұрын
yeah no wtf
@user-rl8li1hq8c9 күн бұрын
I love seeing how long it takes to get 1 working script from chatgpt. i would give a prompt with the minimal requirements and keep sending gpt its own code and the errors i get. i call it "doing the rubics gpt". it's when you keep trying to get gpt to make something and you realise that it ends up on a previous version again after a couple tries before succeeding.
@josiprajkovic97079 күн бұрын
JEsus, we can only taste how complex human system actually is, that is - only how we see things and recognize!
@pappapez9 күн бұрын
Rich Hickey said it best: kzbin.info/www/bejne/l4Sogpmng76Bd8Usi=BszwF9_3VXBVRGOH
@Isaac-eh6uu9 күн бұрын
AI is worse at writing test than writing functioning code.
@dievas_10 күн бұрын
Learn to prompt then...
@eugenedatsmee10 күн бұрын
Why not just use 100% qwik? Apart from having existing code written in astro, if I am starting from scratch, whats the other use case of combining astro and qwik?
@TyrantsAndTyranny10 күн бұрын
Could you stfu about things that aren't in the title and just do the thing in the title. Holy Hell. How many times can you repeat the same re-parsed sentence in the first three minutes.
@DredragonAustin11 күн бұрын
cool plugins
@michaeltse32112 күн бұрын
Part of the motivation to code and learn to code is the feeling of solving a problem. this takes away the joy of coding - lol - but brilliant idea!
@AndrewFloatrx13 күн бұрын
nextjs server actions 😊
@greasy_beefcake13 күн бұрын
Thank you for this
@iansmith330114 күн бұрын
Does this require a paid OpenAI subscription?
@user-fh2fm7vr4m14 күн бұрын
link?
@technicalboy181615 күн бұрын
Get lost.
@enverusta781115 күн бұрын
In my opinion, ts already does that if you put type before the initialization: type Color = { r: number, g: number, b: number } | string; const red: Color = 'red' const blue: Color = { r: 0, g: 0, b: 255 }
@aviralsrivastava405915 күн бұрын
This will be amazing 🔥🔥🔥
@user-iy9fr5td2f15 күн бұрын
What about UI?
@yuvrajchhatwani16 күн бұрын
Its not free it need open ai key
@R_Y_Z_E_N16 күн бұрын
Before , ai was used as SDE , now its an SDET 😂 . I liked you approach , but worst case it can take more time than normal . But best case it improves the code quality . 😊
@kiosk-design16 күн бұрын
How does this effect screen readers ability to scan the page?
@Shemhamforaesh16 күн бұрын
So what AI can we use? Since we cant use ChatGPT's API, its not free
@warguy647416 күн бұрын
then ask ai to write tests that need to pass another test and vice versa
@Alex-ju2lo16 күн бұрын
Thank you for your introduction of the tool. Do you know if there are some plans to integrate it with Azure openai?
@amaldev415016 күн бұрын
Now I have to debug LLM written tests!?
@_Zie_16 күн бұрын
You're just moving the goalposts, now you have to write and debug tests. A broken clock is right twice a day. How about we as programmers stop making our projects by slapping layer upon layer of shitty code on top of eachother and actually just write decent programs, like people who actually understand computers and programming do.
@moises3212316 күн бұрын
Just code your stuff 😂
@mohammedmiftah766316 күн бұрын
If the code ia not scraping or consiming an external api... i just asked it to compile and test it itself. Sometimes it works😅
@AlexAegisOfficial16 күн бұрын
so its tdd for ai btw this is what I mean when I say LLM's are low level components, they arent bad, we're just not building actual tools with it
@danielmontilla591516 күн бұрын
nice. now we need a tool to test the test to make sure the test is correct
@minoakkyaw16 күн бұрын
we might also need a tool to the tool to test the test to make sure the test is correct
@suprimgolay92217 күн бұрын
it feels like cleaning someone shitt 😅
@geekwithabs17 күн бұрын
Love the concept. 🎉
@Danzlh17 күн бұрын
that’s cool. TDD with ai!
@ryujin220617 күн бұрын
Please dont tell me i will go to the website and itll say, basic pricing starts at $500 a month 😂
@upulwaruna.abeysinghe17 күн бұрын
can i share d link to download
@jrnxf17 күн бұрын
perfect explanation. thanks for keeping it short!
@j.r.r.tolkien872418 күн бұрын
This is like flat-earth society denying scientific advancement. lol
@larsh856018 күн бұрын
Interesting. I have for some time held the belief that to improve LLM coding you would need something like this. Good to see you working on this. Beyond "tester" and "coder" personas I'd like security and software quality personas as agents also.
@taheralipatrawala730019 күн бұрын
there's a logical interpretation gap between human problems and what AI can innately understand and solve. Once the gap is filled we may never face any problem with AI ever again. The workarounds like this one may be obsolete once the models get better
@gaggioaxel18 күн бұрын
This model has limited capabilities by structure. Not always predicting the next word (which is what this model does) is the correct solution to a problem. Some problems cannot be tackled by predicting a word. Just give it some math equations and you will see how this concept does not apply correctly. It just gives you the best results that please your ego. I’ve tried putting my university scores and it overestimated my average. But that’s also how the system was trained. To provide polite answers that are liked by the annotator rather than provide correct answers.
@danteDeveloper19 күн бұрын
Is this adding proxy somewhere in runtime?
@k_alex20 күн бұрын
You wasted the first six minutes talking about other stuff.
@AI_Sage2920 күн бұрын
Really loved the idea of microagents. Since i have been building and playing around with AI Agents, I am thinking of implementing one from scratch in python. Why? For fun