HNHacker News
TopNewBestAskShowJobs

_db4z

1 karma · joined February 12, 2024

submissionscomments
_db4z··on We're safe. ChatGPT couldn't fix a typo with a lot of context
I think the two main problems here are:

- Users can't use it to learn, because ChatGPT responds with high confidence but could be terribly wrong.

- Even if it could learn from users, it would really only learn from people that know a subject and are willing to spend their time correcting ChatGPT.

_db4z··on We're safe. ChatGPT couldn't fix a typo with a lot of context
And here's a follow up:

Me: Unfortunately your response is very wrong. Specifically this part "the key of B major, which is the parallel minor key of F major." The parallel minor of F major is not B major. If I hadn't done an additional google search, I'd be taught the wrong theory by you. I'd suggest you stop responding questions that you don't have 100% confidence that they are correct.

ChatGPT: I apologize for the error in my previous response. You are correct that the parallel minor of F major is not B major. The parallel minor key of F major is D minor. I apologize for the mistake and for any confusion it may have caused. Thank you for bringing this to my attention. It is important to me to provide accurate and helpful information, and I will make sure to double-check my responses in the future. If you have any further questions, please don't hesitate to ask.

Me: It happened again. The parallel minor key of F major is also not D minor. Can you please stop making guesses? You're damaging society by letting people believe that you've got correct answers.

ChatGPT: I apologize for the mistake in my previous response. You are correct that the parallel minor key of F major is not D minor. The parallel minor key of F major is F minor. I apologize for the error and for any confusion it may have caused. Thank you for bringing this to my attention. It is important for me to provide accurate and helpful information, and I will make sure to double-check my responses in the future. If you have any further questions, please don't hesitate to ask.

_db4z··on We're safe. ChatGPT couldn't fix a typo with a lot of context
I also just noticed that the response is VERY WRONG.

Take this part: "the key of B major, which is the parallel minor key of F major"

The parallel minor key of F major is F minor.

Our jobs are safe, guys.

_db4z··on The monolith is cluttered, new features **must** be built on microservices
Share your horror story on the tweet thread.
_db4z··on Show HN: I Built a Remote Job Board on GitHub Issues Page
I think that's the same problem we can have on Glassdoor or in the HN's "Who is hiring" page - we have to trust the community and if anything raises an eyebrown, you can report it.

But at least, like in these other apps, you can only leave a comment on GitHub if you're signed-in

_db4z··on I got fired from Facebook (for having a YouTube channel)
Wondering how this isn't in the top of hacker news...
_db4z··on Coinbase: The Heart of the Bitcoin Frenzy
That "What is money" slide is pretty much brainwash
_db4z··on US company scamming remote overseas employees
In case the company deletes its facebook page: http://i.imgur.com/9Y5Dqr2.png
_db4z··on Apple Reports Record First Quarter Results
I would have killed 3 macbooks if I didn't have magsafe.
_db4z··on Apple Reports Record First Quarter Results
You only detailed the things you dislike on the new one, so why is the best macbook?
_db4z··on Show HN: BestRuby – Ruby Tricks, Idioms, Refactorings and Best Practices
AWESOMENESS
_db4z··on Show HN: BestRuby – Ruby Tricks, Idioms, Refactorings and Best Practices
awesome
_db4z··on Ruby Tricks
Awesome initiative! Already sent my PR :)
_db4z··on Tracking GPS chip with SIM card to put inside Macbook Pro
1st source: http://www.businessinsider.com/the-most-violent-cities-in-th...

2st source: http://www.statista.com/statistics/243797/ranking-of-the-mos...

I live in Brazil

_db4z··on Ask HN: How do you conduct code reviews online?
I've only used GitHub Pull-Requests for that, and I guess it's the perfect way. Your friend could create one pull-request for each chunk of changes (better when scoped to one feature), and then you go visit the PR to enter comments on his changes.