I’ve been using deep research more lately (ChatGPT and Gemini) and I’m… VERY impressed. Things changed a lot when I started thinking with a “researcher’s” mindset.

I’ve already derived one research from another (and followed the same steps). Both invalidated my hypotheses 🤡 but elegantly, and bringing the points.

There’s still a problem with the sources they bring, but in ChatGPT I managed to steer it well. One of the tests was that it could only use “peer-reviewed” articles with a high impact factor… and it complied. However, I don’t know how the models indexed articles behind paywalls… I guess they do what most researchers do.

By the way, all the researches did a better job than I do when researching.

Originally written in Portuguese and published on LinkedIn on June 10, 2025. I translated it into English with the help of AI (Claude): it let me bring my LinkedIn posts to people who don’t read Portuguese without rewriting each one from scratch. I reviewed the translation to keep my original meaning and tone.