OpenAI for Developers: How to Use AI for Coding, with Tom Chant
π About the episode
Meet Tom Chant π¬π§! Tom is a Scrimba instructor who has just released a course on building your own AI apps! In this episode, he joins Alex to discuss everything about AI for developers. You'll find out how AI can augment your skills. You'll learn how to use ChatGPT, Codex, and GitHub Copilot, all powered by OpenAI, what their limitations are, and where they overlap.
Tom will also give you useful tips for prompt engineering. You'll hear about the ethical and security risks of using AI when writing code. You'll also get to know how you can train your own ChatGPT model for a specific use! Finally, Tom and Alex also discuss the future of AI. Will coders be replaced with AI language models? Spoiler alert: nope.
π Connect with Tom
β° Timestamps
- What AI tools can developers use in their coding today? (01:11)
- GitHub Copilot vs. ChatGPT for coders (02:57)
- Why is generating code with GitHub Copilot superior? (04:34)
- What is prompt engineering and how to get better at it (06:01)
- What parameters can you tweak when using the OpenAI API to get more customized results? (10:08)
- Using AI for debugging (13:03)
- The downsides of using AI: security risks and false information (15:05)
- How to find balance and use AI wisely (18:08)
- Ethical considerations of using AI for coding (19:50)
- Why some companies arenβt okay with developers using ChatGPT (23:31)
- Community break! Your tweets and LinkedIn posts with Jan The Producer (25:25)
- Tom taught English before joining Scrimba (27:27)
- Why student examination is broken, and how AI might help change it (28:19)
- Whatβs in Tomβs OpenAI course (30:49)
- How to train and fine-tune your own ChatGPT using OpenAI API (35:07)
- Why does training data need to be checked by a human, and can you automate that (41:01)
- How will developers and AI coexist in the future? (43:21)
π§° Resources Mentioned
βοΈ Leave a Review
If you enjoyed this episode, please leave a 5-star review here and tell us who you want to see on the next podcast.
You can also Tweet Alex from Scrimba at @bookercodes and tell them what lessons you learned from the episode so they can thank you personally for tuning in π Or tell Jan the Producer he has butchered your name here.
