34 thoughts on “Micro Agent, a New AI Coding Agent, in 60 Seconds”
Why are developers so determined to use the OpenAI api to write anti-intern / company lay off tools? Coding and writing tests is like the one aspect of being a swe that is fun and why most of us wanted to become swe.
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.
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.
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
Writing good tests means you understand what you need. But our job is usually spent thinking what you need. Sure AI can perfectly define an email validator but not all problems are not well defined like that.
Why are developers so determined to use the OpenAI api to write anti-intern / company lay off tools? Coding and writing tests is like the one aspect of being a swe that is fun and why most of us wanted to become swe.
Damn assert based AI programming
Can I use this for my web app?
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.
Learn to prompt then…
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!
What about UI?
Its not free it need open ai key
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 . 😊
then ask ai to write tests that need to pass another test and vice versa
Now I have to debug LLM written tests!?
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.
Just code your stuff 😂
If the code ia not scraping or consiming an external api… i just asked it to compile and test it itself. Sometimes it works😅
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
nice. now we need a tool to test the test to make sure the test is correct
Love the concept. 🎉
that’s cool. TDD with ai!
Please dont tell me i will go to the website and itll say, basic pricing starts at $500 a month 😂
can i share d link to download
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
Writing good tests means you understand what you need. But our job is usually spent thinking what you need. Sure AI can perfectly define an email validator but not all problems are not well defined like that.
Nice, now i have to debug ai tests and ai code!
Be careful about the api costs. 😮😮
Nah this is not solving any problem its just trying to find a problem for your solution …. BY doing extra work …….
Looks pretty useful ! I’d love to see if it could be used with codestral (or similar) via ollama
Skills issue 😂
Shouldn’t the human write the test?
Cool idea, it would be good to have something like TDD agent that helps you iterate on tests and keeps on adding functionality.
So you have to pay for each test you do to OpenAI. You can create your own GTP for testing purpose.
So the AI is doing TDD
Thanks
Tell me you never used ai to create tests without telling me you never used ai to create tests.
So, when the test is shit your code will be shit as well 😂