171–180 of 352 posts
It's interesting to see 20th century sci-fi depictions of this kind of AI/Search is being short and to the point. I guess they can't have imagined what a mealy mouth world we live in.
Only tried chatGPT 3.5, but my god does it waffle on. Everything I ask ends with a paragraph saying "It's important to remember that..." like an after-school special from a 90s show. It can never just give you code, it has to say "Sure!, to {paraphase your question}, open a terminal...". It's interesting to see 20th century sci-fi depictions of this kind of AI/Search is being short and to the point. I guess they can'…
Only tried chatGPT 3.5, but my god does it waffle on. Everything I ask ends with a paragraph saying "It's important to remember that..." like an after-school special from a 90s show. It can never just give you code, it has to say "Sure!, to {paraphase your question}, open a terminal...". It's interesting to see 20th century sci-fi depictions of this kind of AI/Search is being short and to the point. I guess they can'…
I think we are past the magical talking dog stage and being amazed that an LLM is able to output a Fibonacci function doesn't really help with the progress. As others have commented, this page is a step in the right direction (except the Fibonacci part :).
That being said, the fact that the questions are now online will make them part of the training set sooner or later. Which is to say the only way to reliably evaluate an LLM is by not leaking the test set and being deliberately opaque about what's being asked. Which raises some interesting trust questions.
Earlier quoted context omitted.
It's certainly RLHFed. All of the logic puzzles I use for evaluation that used to fail months ago now pass no problem and I've even had a hard time modifying them to fail.
This is sort of a bummer because it’s not actually an improvement to the model, but just a patch job to artificially inflate performance. All it does is make true evaluation more difficult. Classic “you get what you measure”.
Here is hope they use something like category theory mixed with philosophy to put it on a secure foundation
Earlier quoted context omitted.
But why are there discrepancies in the floating point arithmetic? They have errors when approximating the reals, but floating point operations are all well-defined: even if 0.1 + 0.2 != 0.3, it's still always true that 0.1 + 0.2 == 0.1 + 0.2. I figure the issue must be something related to concurrency in a fleet of GPUs during inference, but even then it's not clear to me where the nondeterminism would creep in. Mayb…
Floating point math is not associative: (a + b) + c != a + (b + c) This leads to different results from accumulating sums in different orderings. Accumulating in different ordering is common in parallel math operations.
> Sally (a girl) has 3 brothers. Each brother has 2 sisters. How many sisters does Sally have? The site reports every LLM as getting this wrong. But GPT4 seems to get it right for me: > Sally has 3 brothers. Since each brother has 2 sisters and Sally is one of those sisters, the other sister is the second sister for each brother. So, Sally has 1 sister.
Only tried chatGPT 3.5, but my god does it waffle on. Everything I ask ends with a paragraph saying "It's important to remember that..." like an after-school special from a 90s show. It can never just give you code, it has to say "Sure!, to {paraphase your question}, open a terminal...". It's interesting to see 20th century sci-fi depictions of this kind of AI/Search is being short and to the point. I guess they can'…
Have you tried asking it to not do those things?
Earlier quoted context omitted.
Have you tried replicating via the API with a temp of 0?
Using a temp of zero usually returns garbage results from most models, so it would likely do so in case of GPT 4 as well. Any other great ideas?