Hacker News new | past | comments | ask | show | jobs | submit | ajonit's favorites login

>dogs and birds react before an earthquake

Earthquakes have what are called primary (P) and secondary (S) waves. The primary is a sharp high frequency wave and the secondary waves are a lower frequency rumble that you feel as the earthquake. The P wave propagates faster so if you're distant from the epicenter the P waves might arrive fractions of a minutes earlier. That's what you see in videos of dogs jumping up and running off or birds taking flight "right before" the earthquake.


I've been using the openai apis to write and edit code for 3-4 months now. So I think that makes me an old timer (ha!). I have also been building tooling for improving the chat based coding experience [0]. All of this work has given me an opportunity to think about how to work best with GPTs on coding, and I've shared some thoughts about this in the past [1].

Here are some of my thoughts on how to code with chatgpt. Many overlap with topics covered in the Nature article.

  - It really does help to think of chatgpt as a junior coder. I mentioned this in the writeup about my first AI coding project [2]. A bunch of things in this list would also be helpful when working with a junior dev.
  - GPT isn't good at code architecture. It will repeat code and take the shortest, laziest path to coding up your request. You need to walk it through changes like you might with a junior dev. Ask for a refactor to prepare, then ask for the actual change. Spend the time to ask for code quality/structure improvements.
  - Don't copy-and-paste between a chat session and your files. Use a tool like Copilot [3] or aider [0] that will give GPT your code to edit and apply its changes automatically. This is critical as it removes friction and lets you iterate quickly on code with GPT.
  - GPT is amazing at generating fresh new self-contained code. It takes more skill and better tools to work with it to edit existing code.
  - Break down a big change and ask for a series of smaller, self contained steps. This is a smart way to code solo, but really helps GPT succeed at more complex code modifications.
  - GPT has a wide breadth of coding knowledge, and impeccable command of syntax... but it is sometimes overconfident about details. So it will usually choose the right library for a task, but sometimes make an error about the details of the api/method/params. Paste doc snippets or error messages into the chat and it will fix those bugs.
  - GPT is really strong at churning out good boilerplate and roughing in a solution. This reduces the activation energy required to start larger changes or changes which will require unfamiliar libraries/packages/languages. GPT can can quickly prepare the ground for you to do the interesting work.
  - If you can, use gpt-4 (not gpt-3.5-turbo) since it can successfully generate larger, more complicated code changes.

[0] https://github.com/paul-gauthier/aider

[1] https://news.ycombinator.com/item?id=36020809

[2] https://github.com/paul-gauthier/easy-chat

[3] https://github.com/features/copilot


And when it happens to you, Google will let you know that they reserve the terminate your account for any reason or no reason at all. You will get the same email response over and over again:

“We have concluded the review of the information you’ve submitted. To prevent possible fraud and abuse, your Google products and services will remain suspended. It is our policy to not discuss the specific reasons for these suspensions.

Note that in the Google <PRODUCT> Terms of Service, we reserve the right to change, suspend, or discontinue any aspect of our services at any time, including availability of a service or any feature, without notice and without liability. We also reserve the right to impose limits on certain Service features or restrict access to some or all of the Services without notice and without liability.”

It can wreck your life. Getting a suspension lifted can take a truly stupid amount of effort depending on the reason (if you even know it). For me it involved basically stalking employees until I was able to find someone who could actually review my account. Literally looking up employees by department and name on LinkedIn and Twitter, then trying to find their phone number and texting them. I must have sounded crazy. But I was able to find someone to help. Then it took like 5 minutes to fix. It was clear it was just a mistake on their end—an, “overzealous anti-fraud algorithm.” I probably spent around 60 hours in totally trying to get my account restored.

After getting access back I stopped using that account and made sure to distribute access to different accounts and emails. Using a single Google account is just way too risky. The more services you use the more likely you are to encounter an account suspending issue. I’ve heard of many cases where people get hacked and Google’s response is to ban the victim permanently. Facebook has similarly atrocious policies.


I can't believe https://futurecoder.io/ hasn't been mentioned!

It has an integrated Python environment in the browser, so the learner can hop right in! That's not even the best part though; I love how well simple concepts are explained. I've been programming for a long time, so there are a lot of things that I forgot aren't a given. futurecoder explains those things really well.

I really cannot recommend it enough! It is a bit pricey though.. JK it's FREE! They don't push it a lot, but they do have an opencollective if you should feel so inclined to donate [0]. I'm not affiliated; just a relative of someone who benefited.

[0] https://opencollective.com/futurecoder


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: