The "reasoning" models and the image generation models are not the same technology and shouldn't be compared against the same baseline.
Kuvwert
joined 2 years ago
Note that my tests were via groq and the r1 70B distilled llama variant (the 2nd smartest version afaik)
Edit 1:
Incidentally... I propositioned a coworker to answer the same question. This is the summarized conversation I had:
Me: "Hey Billy, can you answer a question? in under 3 seconds answer my following question"
Billy: "sure"
Me: "How many As are in abracadabra 3.2.1"
Billy: "4" (answered in less than 3 seconds)
Me: "nope"
I'm gonna poll the office and see how many people get it right with the same opportunity the ai had.
Edit 2: The second coworker said "6" in about 5 seconds
Edit 3: Third coworker said 4, in 3 seconds
Edit 4: I asked two more people and one of them got it right... But I'm 60% sure she heard me asking the previous employee, but if she didnt we're at 1/5
In probably done with this game for the day.
I'm pretty flabbergasted with the results of my very unscientific experiment, but now I can say (with a mountain of anecdotal juice) that with letter counting, R1 70b is wildly faster and more accurate than humans .
Non thinking prediction models can't count the r's in strawberry due to the nature of tokenization.
However openai o1 and deep seek r1 can both reliably do it correctly
If you say so, bud
Hi Michael, Ive made a bug report on your github covering my issue.
I should clarify its not your code causing me issues, Ive quite enjoyed filestash as a base.
The problem has consistently been the office doc viewing integration. Onlyoffice did not reliably allow me to share documents without issue, and the new collaborra integration isn't functional using the default docker compose.
Do you happen to have a docker compose script on hand that allows for multiple different office doc integrations that I can swap between in /admin?
That way when one stops working I can use an alternative?
I'm not even going to attempt to explain it, you seem much too dense. :(
I mean you can think what you want but there is an objectively correct definition:
https://www.merriam-webster.com/dictionary/African%20American
I think 2,3, and 4 are correct but...
African-Americans aren't personally from Africa, but Elon Musk was literally born in Africa: https://en.wikipedia.org/wiki/Elon_Musk
According to this random internet stranger who heard it 2nd-hand over three decades later :)
!The armed guerrilla Shining Path of Peru has repeatedly threatened to kill those found with indelible ink stains to dissuade from participation in elections.!<
My father was in Peru for a time in the 90's and told me that some areas had gangs that would target specific ink colors that were determined by the recipient of your vote. If they didnt like your color they would just kill you :)
view more: next ›
I roll my eyes every time somebody brags about sticking it to big Corp by messing up captchas.
Your data is discarded if its below an expected level. You're causing exactly 0 inconvenience and wasting your own time unfortunately. There are much better ways to hurt google