Hacker News: RobCat27

New comment by RobCat27 in "Claude Code 2.0"

RobCat27 — Tue, 30 Sep 2025 04:17:50 +0000

I've enjoyed using it for coming up with the structure of a project. I'll ask in search mode for structures of other similar projects if I'm not sure. I also enjoy making human-readable .md or .txt documentation files for myself very quickly with it.

New comment by RobCat27 in "AlphaFold 3 predicts the structure and interactions of life's molecules"

RobCat27 — Wed, 08 May 2024 17:43:20 +0000

I believe this is the case also. With a well enough performing AI/ML/probabilistic model where you can change the model's input parameters and get a highly accurate prediction basically instantly, we can test theories approximately and extremely fast rather than running completely new experiments, which will always come with it's own set of errors and problems.

New comment by RobCat27 in "This is a teenager"

RobCat27 — Tue, 16 Apr 2024 16:51:24 +0000

I like the message, but I feel like this is bad data visualization. The width of each group of people is not the same, so it's somewhat meaningless to visually compare groups without being able to see the raw percentages. For example, the "Many Adverse Experiences" group is stretched to be longer than the other groups so that proportionally fewer people in that group appear to be a larger proportion than the same proportion would be in other groups because they're not as wide.

New comment by RobCat27 in "Advice to young people, the lies I tell myself"

RobCat27 — Thu, 04 Apr 2024 17:52:37 +0000

Especially since commonly followed wisdom seems to be "trust, but verify."

New comment by RobCat27 in "Apple and Google avoid naming ChatGPT as their 'app of the year'"

RobCat27 — Thu, 30 Nov 2023 13:35:58 +0000

I've found that for questions that aren't super complex on things that are extremely likely to be in its training dataset (such as public documentation of popular Python libraries) the error rate is very close to 0%. Even compared to GPT from a few months ago I've found the accuracy of responses has increased dramatically.

I still believe anyone using these tools on a day-to-day basis should have a sense of "trust but verify."