Using ChatGPT to write code, tests and essays – game over for engineers or just the next power tool? In this episode of SEEK Bytes, engineers Nick Skoufis, Bridget Barnes, Elliott Millar and Reyna Tan dive into what ChatGPT really is, where it shines, where it fails hard, and how it might change the day‑to‑day reality of software work.
From asking it to refactor test suites, generate React and Webpack configs, or even build a text‑adventure Zork clone, through to security, cheating in coding tests, and mass tech layoffs, they unpack the hype, the risks and the genuinely useful ways to bring large language models into your toolbox – without handing them the steering wheel.
In this episode, we explore:
• How ChatGPT actually works under the hood (tokens, probabilities, “confidently wrong” answers) – and why you still need humans in the loop
• Real‑world uses for developers: refactors, boilerplate, documentation, internal Q&A and dreaming about private, company‑only instances over your own codebase
• What AI means for jobs, interviews and academia – from automation and coding tests to who actually gets replaced (and why that probably isn’t great engineers)
If you’re a software engineer, student or tech lead trying to figure out how to use ChatGPT without letting it use you, this episode is for you.
🔔 Follow the SEEK Bytes podcast so you never miss a new episode