Show HN: I wrapped the Zorks with an LLM • Hacker News Board

Re: Show HN: I wrapped the Zorks with an LLM

#61

Post by waffletower » Wed, Jan 28, 2026, 4:16 PM UTC

grouchy wrote: post #2

I'm not from the era of these games, but I remember trying them and finding them frustrating for the same reason. But when I tried this, I literally couldn't stop. I could just write some random action. It's actually amazing to me how many situations they were able to consider in the game, but having the LLM translate my language into the right action made the game feel way more natural. I'd be interested in seeing h…

They were way too rigid then, and still too rigid now after my brief attempt lol. Such a narrow puzzle you have to squeeze into.

Re: Show HN: I wrapped the Zorks with an LLM

#62

Post by DonHopkins » Wed, Jan 28, 2026, 9:01 PM UTC

almosthere wrote: post #37

joelcares wrote: post #27

Earlier quoted context omitted.

Ok, I refreshed and tried again. Climb in mailbox You approach the small mailbox and try to climb inside, determined to fit yourself within its confines. You attempt to climb into the small mailbox, but end up bumping your head against its narrow opening. It's simply too small for anyone to fit inside; only letters and parcels can enter here. Become a letter You focus deeply, willing your body to transform. You feel…

Can you get out of the mailbox now that you're a letter?

Try addressing the letter to yourself and waiting!

Re: Show HN: I wrapped the Zorks with an LLM

#63

Post by spopejoy » Thu, Jan 29, 2026, 3:51 PM UTC

Amazing!

I was able to confuse the llm with the following command while in the living room: "go back outside and find mailbox" (which I had forgot to check before going in the window)

It got super confused, went in and out the window three times. It did actually recover and plop me outside suggesting I head north and west. Good times!