Read more in my latest blog post: #javascript #ai #typescript #react #figma
Code The Future
By
admin
#AI, #ai tools for coding, #chatgpt se ppt kaise banaye, #free ai tools, #how to make ppt, #how to make ppt in hindi, #how to make ppt in hindi using chatgpt, #how to make ppt in hindi using free AI tools, #how to make ppt on mobile, #how to make ppt presentation with pictures on laptop, #how to make ppt using ai, #how to make ppt using chatgpt, #how to make ppt using chatgpt in hindi, #latest ai tools, #PowerPoint presentation, #ppt, #ppt kaise banate hai, #ppt kaise banaye, #ppt presentation, #ppt slideshow on laptop
Read more in my latest blog post: #javascript #ai #typescript #react #figma
more on what you can do with micro agent in my latest post: https://www.builder.io/blog/micro-agent
But then the problems it fixes still exist in the test itself. The tests are more likely to be full of errors themselves. Then what? Ask it to make a test to the test, infinitely? Fix the test yourself? That'd go against the whole point of the agent.
Can we use Claude sonnet?
steve, ive been following all this ai videos and your approach of instead having big models, to create mini/micro/small models/agents to solve "one" problem. great work, man! you are inspiring
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 ?
So what AI can we use? Since we cant use ChatGPT's API, its not free
Thank you for your introduction of the tool. Do you know if there are some plans to integrate it with Azure openai?
it feels like cleaning someone shitt 😅
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.
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
Looks fantastic! Excited to try it!
By YouSum Live
00:00:00 Frustration with traditional AI code generation
00:00:32 Proposal of a micro agent for code generation
00:00:40 Micro agent converts prompts into tests first
00:00:57 Iterative code development based on test results
00:01:06 Clear success criteria through test-driven development
00:01:18 Feedback loop enhances AI's debugging capabilities
00:02:26 Integration of microagent into development workflow
00:02:45 Future applications of microagent in diverse use cases
00:03:05 Continuous improvement and feedback encouraged
By YouSum Live
I tried making the same thing in December last year. But the problem I kept running into is that the tests themselves are wrong af. I soon gave up on the project
does this also have context of your project? For example, can you tell him to check a file and try to fix it?
Steve, you don't regularly upload but when you do it's always great content.
I know it's just an example, but it implemented groupAnagrams in O(n * mlogm) where n = strs.length and m is avg size of a given string when in fact you can do all that all in O(n * m) without the sorting.
And therein lies the problem with AI code slop. Imagine if the code implementation was much longer and complex; these things become harder to spot, especially once you get used to them. Don't get me wrong though, I still think this approach is very very useful in other domains of work (Figma, prototyping, etc). I just wouldn't use micro agents for code gen in any real setting.
TDD
ugh gpt again. Use gemini or groq!
Steve ily
The entire flow living inside command line might be somewhat annoying
The quality of the final output depends on the quality of the tests
If we could edit the tests in vs code and then just have a command that gets a test file and outputs the implementation that would be great 🙂
can't get enough of programmers making themselves redundant or dumping their own salary levels…
Interesting but now you have to be confident that the generated tests actually catch all edge cases.
Okurrr
another great AI Tool from Steve!
I would really like to use it with a local model (e.g. via oIlama). Can or will you provide a solution for this?
Bro out here droppin' gems!
great
awesome that smth this simple works that good
I love your work Steve, This looks fantastic and really practical. Thank you!
This looks awesome. I'm eager to try it! Thanks for sharing.