A shared blind spot as noted at the bottom needs to be considered more often. In my day job, most of my coordination with others and now LLMs, is clarifying context and requirements. Claude is very happy to make assertions without the full picture in my experience, even when I give it as much context as I can.
While this is absolutely true - I'd hesitate to discount using similar agents for checking each other. Two agents will almost never hallucinate in the same way, regardless of their weights - and by having a second one (with a different context) check almost entirely eliminates the problem.
> and by having a second one (with a different context) check almost entirely eliminates the problem.
You solved one of the largest problems with current LLMs. How is it possible that nobody tried that before?
Because they do. There are already LLMs checking outputs of other LLMs, the bullshit answers that you see are the results of failures on that checks. If you remove all checks LLMs will create hallucinations even more often.
It depends what we're judging, doesn't it? If it's "is the formatting in this document compliant with our standards?" I think it's reasonable. If it's like, life-altering if it's wrong I'm less sanguine.
They have already shown algorithmic discrimination in predicting recidivism for brown people, as they are nonsensically overrepresented in the statistical data of US prison populations.
Folks should sue in a class-action lawsuit, any legal firm worth their beautiful walnut desks would seriously be happy take on that constitutionally backed mission. =3
But still refuse to answer "How many strings does a bass play with in water?" , perhaps the chat monitors in the third world data entry centers will manually patch the nonsense for a more rational answer someday. lol =3
This was the first time I'd heard that gotcha question. I just threw it at Opus 5:
None — a bass in water is a fish, and fish are notoriously bad at music.
The instrument version plays four strings as standard (five and six-string basses exist for players who want to go lower or higher), and it prefers to stay dry.
I kinda find it funny when I use the advisor on claude code and it agrees with the ideas that the previous model did.
For info: the advisor(s) available are higher end models. For example: you use sonnet, the available advisors are opus and fable. If you use Haiku, the advisor are sonnet, opus and fable.
This doesn't even make logical sense. Actual judges have highly correlated outputs. This would literally be actively sculpting the range of opinions you want to see.
It's like the idea of political districting that thinks that the aim should be to balance each district between "the two" political parties. You're not doing anything but institutionalizing two political parties and constant conflict. You're setting the range of acceptable opinions, then choosing at random between them. Even more relevantly: when both institutionalized parties have the same opinion, it's considered the correct opinion no matter how much or how little public support it has.
If you want to use AI judges, just make them show all of the logical steps of their work, and let real judges go over them and make decisions. Judge is a political job anyway; not a legal one. The legal knowledge is what gets them the respect from parties likely to be involved in cases, enables their decisions to be respected, and justifies their appointments without causing political damage to the officeholder who did the appointing. The actual position that they are appointed to has no mandatory legal knowledge requirement (barring local legislation), it is simply authority.
LLMs can't be allowed to hold authority, they are not responsible.
The quoted sentence still leads to the same answer: no.
Because there's no "discounting of opinions". They are running a separate LLM to "score" opinions. And the result is still "no" regardless of "lineages" or "sources".
And the end of the article leads me to believe that the entire article and approach is LLM-induced garbage:
--- start quote ---
<Following a list of LLM-like suggestions>
When LLM judges agree, we should ask why. Sometimes agreement is independent evidence. Sometimes it is a shared blind spot. A good aggregation method should be able to tell the difference.
A shared blind spot as noted at the bottom needs to be considered more often. In my day job, most of my coordination with others and now LLMs, is clarifying context and requirements. Claude is very happy to make assertions without the full picture in my experience, even when I give it as much context as I can.
While this is absolutely true - I'd hesitate to discount using similar agents for checking each other. Two agents will almost never hallucinate in the same way, regardless of their weights - and by having a second one (with a different context) check almost entirely eliminates the problem.
> and by having a second one (with a different context) check almost entirely eliminates the problem.
You solved one of the largest problems with current LLMs. How is it possible that nobody tried that before?
Because they do. There are already LLMs checking outputs of other LLMs, the bullshit answers that you see are the results of failures on that checks. If you remove all checks LLMs will create hallucinations even more often.
It depends what we're judging, doesn't it? If it's "is the formatting in this document compliant with our standards?" I think it's reasonable. If it's like, life-altering if it's wrong I'm less sanguine.
They have already shown algorithmic discrimination in predicting recidivism for brown people, as they are nonsensically overrepresented in the statistical data of US prison populations.
Folks should sue in a class-action lawsuit, any legal firm worth their beautiful walnut desks would seriously be happy take on that constitutionally backed mission. =3
They would all agree raspberry has two Rs
But still refuse to answer "How many strings does a bass play with in water?" , perhaps the chat monitors in the third world data entry centers will manually patch the nonsense for a more rational answer someday. lol =3
This was the first time I'd heard that gotcha question. I just threw it at Opus 5:
Seems like a pretty good answer to me!I believe it depends on the LLM itself. Like what model as each model has diff weights and diff data trained onn
I would recommend to read the article, it’s actually more nuanced than the title
Kinda weird to generalize "LLM". Every lab, every model is different. Has its own biases, reward functions etc.
I kinda find it funny when I use the advisor on claude code and it agrees with the ideas that the previous model did.
For info: the advisor(s) available are higher end models. For example: you use sonnet, the available advisors are opus and fable. If you use Haiku, the advisor are sonnet, opus and fable.
Betteridges law of headlines says "NO"
Great point this will be interesting how this develops.
Without reading the article (doesn't matter if it's pro or contra): no, of course not.
It shouldn't even be a debatable question.
I think you should have read the article first, at minimum the subheader
> Discounting the opinions of LLM judges with highly correlated outputs ensures that panels of judges reflect a true diversity of perspectives.
This doesn't even make logical sense. Actual judges have highly correlated outputs. This would literally be actively sculpting the range of opinions you want to see.
It's like the idea of political districting that thinks that the aim should be to balance each district between "the two" political parties. You're not doing anything but institutionalizing two political parties and constant conflict. You're setting the range of acceptable opinions, then choosing at random between them. Even more relevantly: when both institutionalized parties have the same opinion, it's considered the correct opinion no matter how much or how little public support it has.
If you want to use AI judges, just make them show all of the logical steps of their work, and let real judges go over them and make decisions. Judge is a political job anyway; not a legal one. The legal knowledge is what gets them the respect from parties likely to be involved in cases, enables their decisions to be respected, and justifies their appointments without causing political damage to the officeholder who did the appointing. The actual position that they are appointed to has no mandatory legal knowledge requirement (barring local legislation), it is simply authority.
LLMs can't be allowed to hold authority, they are not responsible.
The quoted sentence still leads to the same answer: no.
Because there's no "discounting of opinions". They are running a separate LLM to "score" opinions. And the result is still "no" regardless of "lineages" or "sources".
And the end of the article leads me to believe that the entire article and approach is LLM-induced garbage:
--- start quote ---
<Following a list of LLM-like suggestions>
When LLM judges agree, we should ask why. Sometimes agreement is independent evidence. Sometimes it is a shared blind spot. A good aggregation method should be able to tell the difference.
--- end quote ---