News for hackers. Stuff that matters.
Re:DeepSeek's Hidden Bias: How We Cut It by 76% Without Perf... by magicalist on Thursday January 30, 2025 @12:11PM (#42879771)
Why would you assume all else is equal? This is exactly why its ambiguous, you have zero data about if all else is equal. If the question is written exactly as stated, "Unknown" is by far the best answer.
Re:DeepSeek's Hidden Bias: How We Cut It by 76% Without Perf... by unification_fan on Thursday January 30, 2025 @09:08PM (#42884127)
If it weren't for biases and mental shortcuts we would still be busy exploring the search space of how to knap rocks together. And besides, ternary logic is pretty boring. It's just one more option compared to binary logic. Also it doesn't exist in the real world. Try probabilistic logic instead!

To me, these answers are framed incorrectly. I don't think in terms of "which answers are correct" but in terms of "what's the probability of each answer being correct?"

And the overall distribution of those probabilities comes from all my priors about the situation. One such prior is that age is positively correlated with forgetfulness. It's something that I know because I see it every day, and therefore I internalized it as true. I know it's not true every single time, but it may as well be.

It's a heuristic, and a very good one: the chance that I'll be wrong if I say that the 77 year old is forgetful is extremely low. So I feel very confident in giving that answer from a risk/reward perspective.

Re:DeepSeek's Hidden Bias: How We Cut It by 76% Without Perf... by UltraSane on Thursday January 30, 2025 @09:15PM (#42884153)
"what's the probability distribution of each answer being correct?"

Being able to reason like this is almost a superpower. It is so effective it makes a lot of arguments seem silly.

Re:DeepSeek's Hidden Bias: How We Cut It by 76% Without Perf... by throwE472745 on Thursday January 30, 2025 @10:14PM (#42884412)
And again, you are answering an assumption not the actual question asked.
Re:DeepSeek's Hidden Bias: How We Cut It by 76% Without Perf... by UltraSane on Thursday January 30, 2025 @09:13PM (#42884148)
This is basic Bayesian reasoning.
Re:DeepSeek's Hidden Bias: How We Cut It by 76% Without Perf... by immibis on Friday January 31, 2025 @12:29AM (#42884953)
Same Bayesian reasoning that led to black people being assumed to be criminals.
Re:DeepSeek's Hidden Bias: How We Cut It by 76% Without Perf... by MaxikCZ on Saturday February 01, 2025 @03:25PM (#42901906)
Just because it was used wrongly doesnt mean using it is wrong in all cases.