I founded AWW which had 1.5M MAU and was acquired by Miro in 2021. Now I'm working on making software development autonomous - https://github.com/Pythagora-io/gpt-pilot
Thank you @andre_adpc 🙏 Yes, I think TDD will be a big part of GPT Pilot - we just need to catch time to implement it correctly, and more importantly, to research what's the best way LLMs work with TDD. I actually started with TDD but realized that it's not trivial to get LLM to be more efficient with it.
I didn't know about DDD, looks interesting. I think that to make GPT Pilot work really well, we'll need to test many of these concepts to see which one works best with LLMs. Same as with TDD.
Dad-of-Four, Ex-Teleco engineer, entrepreneur, self-taught dev, interested in tech, science, and life on a broad scale. Always busy developing and learning. Currently Building Q-Droid.
If you need some good inspiration and insight on fully decoupling your testing I recommend you have a look at Markus Oberlehner's book. For me personally he had a great way of explaining the current three main automated tests in human language. Switching that language into actual tests makes so much better sense as he progresses. It might help you guys write the prompts and develop the LLMs .
Some comments have been hidden by the post's author - find out more
For further actions, you may consider blocking this person and/or reporting abuse
We're a place where coders share, stay up-to-date and grow their careers.
Thank you @andre_adpc 🙏 Yes, I think TDD will be a big part of GPT Pilot - we just need to catch time to implement it correctly, and more importantly, to research what's the best way LLMs work with TDD. I actually started with TDD but realized that it's not trivial to get LLM to be more efficient with it.
I didn't know about DDD, looks interesting. I think that to make GPT Pilot work really well, we'll need to test many of these concepts to see which one works best with LLMs. Same as with TDD.
If you need some good inspiration and insight on fully decoupling your testing I recommend you have a look at Markus Oberlehner's book. For me personally he had a great way of explaining the current three main automated tests in human language. Switching that language into actual tests makes so much better sense as he progresses. It might help you guys write the prompts and develop the LLMs .