neeldhara

Likewise, thanks for checking it out!

Oh yay, thanks for trying it out! Do you have your project up somewhere? I'd love to take a look.

TIL that apparently you can simply use the generic follow up prompt “did you do what I asked?” and it will verify and course correct on its own, see for instance:

https://twitter.com/ericjang11/status/1639882111338573824

No idea how well this works in practice for things like JS games with visual elements, but seemed like an interesting approach!

Have you tried one of the web-based ones? Like Toggl or Rescue Time? Or manual with a custom setup may be the way to go - e.g, my current time tracking is a bunch of markdown files with YAML front matter keeping track of the specifics, and Obsidian (a cross-platform note-taking app) provides the "UI" for viewing the data from these files in a meaningful way. The cost of setting this up is non-trivial: but worth it if you are in it long term IMO :)

That’s true, I did not mean to suggest that ChatGPT authored the game: but I do feel that it partnered significantly in the creation of this specific implementation. Is there a better way to put it?

Thanks for the input!

Aw thanks, this makes my day!

This may have actually been my bad: once chatGPT gave me what I asked for, I would think about it some more and tweak the code manually, especially if it was a low-effort edit. Consequently there will perhaps be some bugs: I’ll fix this one, thanks for sharing!

I hope you do play it for a positive number of rounds though :)

Sheepish is a cool name! Thanks for sharing… I read that review with some apprehension: fortunately, most of the critique appears to be not directly applicable to 13 sheep — phew.

I have to confess I have no professional experience in design, although I do consider myself a moderately picky user :)

I did try to think about what I’d enjoy or be put off by if I was playing — but I didn’t have anything beyond this common sense approach to guide the design choices.

Sheepish sounds like a slightly different game though: it reminds me of a few others (one to do with pipes again and another with laying out train tracks). Will dig these up and share once I do have the pointers. Thanks again!

Oh, interesting! The goal seems in a similar spirit for sure — I think the main difference is the mechanics of how it’s achieved… movable blocks for the rats, but fences made out of specific shapes for the sheep :)

Ah well — that’s fair! I wasn’t sure about the best way to do it, let me see if I can replace the intro prompt with something more welcoming but also brief.

If you have a chance to try it out for longer and it’s still confusing, let me know! I do wish the game calculated your score for you at the end, but as I explain in the blog, this ended up being too complex for the first cut. I hope I can work this out in due course…

Thank you! Indeed, it’s still a fair amount of back and forth, and would have probably been even more frustrating if I didn’t know anything at all about HTML/CSS/JS. I think it’s been pointed out in other contexts that the AI tools can be substantial boost on top of some elementary code literacy, but it will still involve effort (both on the prompt engineering as well as verification and subsequent nudging).

All that said, the experience still felt empowering… in particular, I am not sure that I’d be able to pull this off on my own in a comparable — or even, say, double — the amount of time. So that’s a win overall, I suppose!

Also glad you found the logs useful. Thanks again for taking a look :)

I suppose some of the design choices were guided by the prompts chatGPT got from me, so to be fair I’d be to blame for confusing design. I figure the best way to get the hang of the rules was to play a couple of throwaway games — they are quick to play. However if you can share any suggestions for making the experience more intuitive, please let me know, I’d be happy to try making it better :)

Thank you! :)

I used to use the apps atimelogger (http://www.atimelogger.com/) and atracker (http://www.wonderapps.se/ATracker/home.html) for a year and two years, respectively. I tracked work and certain non-work activities (e.g, sleep and such), and it was very effective. The reports helped with awareness around relative time spent over different projects and such.

While all the tracking was manual, and I tried to do it either in real time or by the end of the day (or at best the next day), it was useful to have some automated time tracking tools for double-checking in recall. For this, I use mostly Timing (https://timingapp.com/) and location tracking on my phone.

Now I use a custom entry system in Obsidian which lets me do more fine-grained reports (e.g, by project) and also has the advantage that I have one app less to worry about. I still have Timing to help with recall though. Some people use Timing exclusively - and it does have several advanced features and a nice UI!

Prompted by a question on Twitter: it turns out that the puzzle is also NP-complete:

https://www.neeldhara.blog/posts/dogs-bunny-puzzle/