[gixco]

I saw a relatively new AI company already valued at over $1 bn publish a "new technique" recently, complete with whitepaper and all. I looked at the implementation and... it was just querying four different models, concatenating the results and asking a fifth model to merge the responses together.

Makes me wish I had spent some time in college learning how to sell rather than going so hard on the engineering side.

[amarcheschi]

I had a startup building course at university and I was kinda shocked when I learnt that VCs don't actually have all the knowledge you have so you have to know how to sell your ideas. Yep, knowing how to sell something at the right person (at the right moment) is just as important as having a good idea

[ianbutler]

The novel part of that paper was not merging the responses. The last model can, from the inputs, synthesize higher quality overall responses than any of the individual models.

It’s a bit surprising that works and your take on it is overly reductive largely because you’re wrong in your understanding of what it was doing.

[gixco]

I didn't just look at the implementation, I tried it as well. I was hoping it would work, but the aggregating model mostly either failed to properly synthesize a new response (merely dumping out the previous responses as separate functions) or erratically took bits from each without properly gluing them together. In every case, simply picking the best out of the four responses myself yielded better results.

[ianbutler]

Interesting, I've seen live demos working fairly well. I've also implemented something adjacent to the work and it works quite well too. I'm not sure why you had a hard time with it.

I am however working in a domain where verification isn't subjective so I know a good response from a bad response fairly easily. Things like this depend quite heavily on the model being used too in my experience.

[ericjmorey]

Use the fifth model to suggest which of the 4 outputs is the best and sell the idea for $10 billion.

[redgetan]

What is the name of the company?

[__loam]

Ensemble models are a real technique but boy do I feel stupid having not gotten into the making api calls to ai models grift.