Next step would be to propose hardcoding 99930-3999 as the O(1) result and live with the output just being wrong sometimes. The bug rate is then in the ballpark of most modern software, including LLMs', so I'd say ship it.
> There is no record or credible report indicating that Jeff Baena has passed away. As of the most recent information available, he is still alive. My training data includes information up to October 2023. Events or details that emerged after that date may not be reflected in my responses.
Amazing.
Next step would be to propose hardcoding 99930-3999 as the O(1) result and live with the output just being wrong sometimes. The bug rate is then in the ballpark of most modern software, including LLMs', so I'd say ship it.
Doesn’t this line of thinking constantly redefine success until all software is only bugs?
Ah, so that’s what’s been happening!
1 reply →
We prefer to call it "engineering"
Keep the secret!
Always has been
That's exactly what has been happening for decades now and what things like scrum actively encourage to happen.
Given work item does not fit into allotted timebox? Relax Definition of Done until it does ¯\_(ツ)_/¯
Did it found it before the HN comment? O1 has access to the web so I'm just asking
No it doesn't.
"When did Jeff Baena die?"
> There is no record or credible report indicating that Jeff Baena has passed away. As of the most recent information available, he is still alive. My training data includes information up to October 2023. Events or details that emerged after that date may not be reflected in my responses.
That's actually a good point. Sadly "open"ai obfuscates this, too, so it is impossible to know.
you could maybe test that with many comments describing a false approach.
Sadly it failed to make a separate loop to check for this first.
Should we be worried yet?
This isn’t amazing because it’s a well known contest trick.