Damn, I just checked a random express project I built and there are a lot of things underlined in red there. I think the most amazing one is https://www.npmjs.com/package/is-number-object, which has a stupidly large dependency tree.

It seems like they just took a template and forgot to remove that part. It doesn't make any sense

I used to use spaceship prompt before this, and it would often take 5s to open up a new terminal and wait for the prompt to load, starship is always instant (like a prompt should be).

I think he is talking about a human using the programatic API the LLMs are using to play the game. I think that would be a whole lot slower than normal playthrough

We were able to pass all the early lab tasks manually - although it took a lot longer than using the UI!

TIL macOS does not have alt+tab, how do you switch windows quickly?

CMD+tilde cycles through the current app's open windows.

It does not, we have to use cmd+tab :(

I assume just copy and paste it

I'm just as confused... If you're copy/pasting the code into a new session, isn't that reading the code?

The way I understand it:

First Variant:

1. User: Asks coding question

2. Ai: Outputs half functioning code

3. User: Asks to fix specific things

4. Ai: Creates buggy code

5. User: asks again to fix things

6. Ai: writes even more buggy code

Proposed second variant with copying code:

Until step 4 everything stays the same, but instead of asking it to fix the code again you copy it into another session, this way, you'll repeat step 3 again, without the LLM "seeing" the code it previously generated for step 4.

I dunno how you SWE's are doing it, but I have my ChatGPT output files and if multi, zip files, not code snippets (unless I want a code snippet), and then I re-upload those files to new session using the attach thinger. Also, in my experience just building marketing websites, I don't do step 3, I just do step 1 and 2 over and over in new sessions, it's longer because you have to figure out a flow through a bunch of work sessions, but it's faster because it makes wwwwaaaaayyyyyyy fewer mistakes. (You're basically just shaking off any additional context the GPT has at all about what you are doing when you put it in a brand-new session, so it can be more focused on the task, I guess?)

tsoding is pretty great too if you are interested in c.