Did OpenAI intentionally handicap GPT4's image modality's ability to identify people?
7
48
Ṁ187Ṁ170
Dec 31
83%
chance
1D
1W
1M
ALL
Various people on twitter report that GPT-4, despite being otherwise skilled at image tasks, often can't recognize people in images. Given OpenAI's past attempts to sand the sharp edges off of their models, it's plausible they trained it to not identify individual people to avoid privacy issues.
Resolves to YES/NO when confirmed either way. N/A if never confirmed
Get Ṁ600 play money
Related questions
Related questions
Did OpenAI achieve weak AGI with GPT-4o?
POLL
Is gpt2-chatbot made by OpenAI?
99% chance
Will OpenAI change their naming scheme (GPT-X) with the successor to GPT-4? (Ṁ200 subsidy!)
17% chance
Will OpenAI's autonomous agent be based on GPT-4?
71% chance
Has openAI intentionally made chatGPT lazy to save inference costs?
21% chance
Will adversarially modified images produced by ANN be confirmed to weakly work on humans?
77% chance
GPT-4 with image recognition wins tictactoe more than half the time against a child level opponent?
17% chance
Will OpenAI suggest GPT-4 is AGI?
4% chance
Will OpenAI provide access to GPT-4 weights to academic researchers not affiliated with OpenAI, by 2025?
18% chance
Is GPT4 sentient?
12% chance