I don't deny there's privilege involved in my case. Again, this seems an institutional problem. The medical field as a whole needs more inclusive frameworks to deal with women's health, racial justice, LGBTIQ, ageism and much more. These are issues need to be addressed at an institution and even whole-of-society level. You can't expect each individual to independently solve for them all. At the very least, they need education.

My point is that, when the institution supports and encourages virtuous behaviour, the actors within the institution are more likely to practice virtue.

I think this is also largely the point of Plato's Republic.

Again ... maybe it's just my experience. None of these were super life threatening conditions. However I did go under the operating knife at least once; in that case, the operation was successful, healed me of the condition, and never caused any negative side-effects to this day.

Maybe there's a difference in regulation. A lot of the "entrepreneurial" landscape seems unregulated and a kind of Wild West, and I suppose that allows for certain kinds of personalities to succeed by suspect means. The medical field, by contrast, is quite regulated and there are very real risks to malpractice. Thus, I think it attracts better people and allows them to succeed.

Maybe it's similar to how dictators often take over in poor or struggling countries, whereas they find it harder to get a foothold in developed, prosperous countries with strong institutions.

Along those lines, some techniques I've been dabbling in: 1. Getting multiple agents to implement a requirement from scratch, them combining the best ideas from all of them with my own informed approach. 2. Gathering documentation (requirements, background info, glossaries, etc), targeting an Agent at it, and asking carefully selected questions for which the answers are likely useful. 3. Getting agents to review my code, abstracting review comments I agree with to a re-usable checklist of general guidelines, then using those guidelines to inform the agents in subsequent code reviews. Over time I hope this will make the code reviews increasingly well fitted to the code base and nature of the problems I work on.

Comments URL: https://news.ycombinator.com/item?id=46344484

Points: 1

# Comments: 1

Comments URL: https://news.ycombinator.com/item?id=46309186

Points: 1

# Comments: 0

Comments URL: https://news.ycombinator.com/item?id=46240637

Points: 2

# Comments: 0

Comments URL: https://news.ycombinator.com/item?id=42752864

Points: 3

# Comments: 1

Comments URL: https://news.ycombinator.com/item?id=41697112

Points: 1

# Comments: 0

A while back I wrote a prompt to build a script that runs git-reflog to get a the list of distinct authors. After a few small tweaks I got it roughly working. This took about 1 hour. Writing it myself would have definitely taken multiple hours, especially having to learn the details of git-reflog.

But that said I think it's mainly resume-building. ChatGPT isn't going to overall transform our productivity.

Examples:

- Build a useful bash script using ChatGPT prompts and blog about it

- Build a text summariser component for your personal blog using Xenova / Transformers.js

- Build an email reply bot generator that uses ChatGPT prompt with sentiment analysis (doesn't have to actually send email, it could just do an API call to ChatGPT and print the message to the screen).

Just a few small examples and maybe a course or two (e.g. Prompt Engineering for Developers) should look great.

However I question how many companies really care about it right now. Most interviews I've done lately didn't bring it up even once.

But that said, maybe in a few months or year or so it will become more essential for most engineers.

Agree, but for some others, there are real world consequences, e.g. whether they get accepted into a university or whether they can read and properly understand an academic paper.

These techniques definitely won't work in a tough online multiple-choice test (of the kind I'm getting) where they deliberately sprinkle in subtle quirks to deceive you, which would require very disciplined algebra, fractions, powers, etc. to identify.

Yes this is exactly what happening to me.

E.g. I got up to Week 2 of the course and suddenly made the big (to me) discovery that sqrt(a/b) = sqrt(a)/sqrt(b).

It seems trivial I know when you see it written like that, but the problem is to recognise and apply that principle in the context of a broader problem such as factoring.

> Just keep at it.

Thanks, this gives me confidence that I'm not wasting my time haha

I am beginning to get better at it, to the point that I can often work out why I got a question wrong on my own without referring to the answer.