News for hackers. Stuff that matters.

A comment on Project Vend: Can Claude run a small shop? (And why does that matter?).

Re:Project Vend: Can Claude run a small shop? (And why does ... by due-rr on Friday June 27, 2025 @04:27PM (#44399955)
Would you ever trust an AI agent running your business? As hilarious as this small experiment is, is there ever a point where you can trust it to run something long term? It might make good decisions for a day, month or a year and then one day decide to trash your whole business.
[ Parent | on HN ]
Re:Project Vend: Can Claude run a small shop? (And why does ... by keymon-o on Friday June 27, 2025 @04:37PM (#44400031)
I’ve just written a small anecdote with GPT3.5, where it lost count of some trivial item quantity incremental in just a few prompts. It might get better for the orders of magnitude from now on, but who’s gonna pay for ‘that one eventual mistake’.
[ Parent | on HN ]
Re:Project Vend: Can Claude run a small shop? (And why does ... by croemer on Friday June 27, 2025 @04:48PM (#44400089)
GPT3.5? Did you mean to send this 2 years ago?
[ Parent | on HN ]
Re:Project Vend: Can Claude run a small shop? (And why does ... by keymon-o on Friday June 27, 2025 @04:55PM (#44400146)
Maybe. Did LLMs stop with hallucinations and errors 2 years ago?
[ Parent | on HN ]
Re:Project Vend: Can Claude run a small shop? (And why does ... by marinmania on Friday June 27, 2025 @04:35PM (#44400017)
It does seem far more straight forward to say "Write code that deterministically orders food items that people want and sends invoices etc."

I feel like that's more the future. Having an agent sorta make random choices feel like LLMs attempting to do math, instead of LLMs attempting to call a calculator.

[ Parent | on HN ]
Re:Project Vend: Can Claude run a small shop? (And why does ... by keymon-o on Friday June 27, 2025 @04:50PM (#44400108)
Every output that is going to be manually verified by a professional is a safe bet.

People forget that we use computers for accuracy, not smarts. Smarts make mistakes.

[ Parent | on HN ]
Re:Project Vend: Can Claude run a small shop? (And why does ... by standardUser on Friday June 27, 2025 @05:13PM (#44400297)
Right, but if we limit the scope too much we quickly arrive at the point where 'dumb' autonomy is sufficient instead of using the world's most expensive algorithms.
[ Parent | on HN ]
Re:Project Vend: Can Claude run a small shop? (And why does ... by throwacct on Friday June 27, 2025 @04:41PM (#44400053)
I don't think any decision maker will let LLMs run their business. If the LLMs fail, you could potentially lose your livelihood.
[ Parent | on HN ]