🤖 Learn about the importance of open source and how developers can best use LLMs in this episode of People of AI. @engineerrprompt sits down with @film_girl and @ashley_oldacre to share his journey from a Ph.D. in Applied ML to a successful AI education YouTube creator. Key Moments: 0:00 Intro 03:15 From Ph.D to YouTube Creator 04:50 First viral YouTube hit 08:20 RAG and why it matters 11:20 The origins of localGPT 15:20 What has changed with building in the last 2 years 18:35 How AI tools and models have matured 19:50 Becoming a technical manager to LLMs 22:20 What agentic coding has enabled Muhammad to build in localGPT 2.0 27:45 Better maintaining open source projects by leveraging AI 28:50 What to watch out for when building with agentic systems 31:20 Advice for junior developers 35:40 Differences between how junior devs and senior devs use AI tools 39:19 Specs-driven development 41:20 Advice for experimenting with AI tools 42:50 The problem with overly-agreeable LLMs 45:10 Why long-context windows are useful for coding 47:30 Advice for someone launching a tech-focused YouTube channel 51:40 Rapid Fire Questions

@googledevs @engineerrprompt @film_girl @ashley_oldacre Open source empowers. It bridges the gap between research and real-world application, fostering faster innovation. This benefits everyone.

@googledevs @engineerrprompt @film_girl @ashley_oldacre I'm also building a lot of software that translates civilization into language. The emergence of language models has enabled me to make an important decision: to breathe life into the best software and hardware.

@googledevs @engineerrprompt @film_girl @ashley_oldacre And since 1000 lines of code per min is way more code than anyone can output i personally suggest using best model possible for code writing since it has the deepest insight