zlacker

[return to "Elon Musk sues Sam Altman, Greg Brockman, and OpenAI [pdf]"]
1. 1vuio0+vn2[view] [source] 2024-03-02 01:59:41
>>modele+(OP)
"In March 2023, OpenAI released its most powerful language model yet, GPT-4. GPT-4 is not just capable of reasoning. It is better at reasoning than average humans. It scored in the 90th percentile on the Uniform Bar Exam for lawyers. It scored in the 99th percentile on the GRE Verbal Assessment. It even scored a 77% on the Advanced Sommelier examination."

One could argue a common characteristic of the above exams is that they each test memory, and, as such, one could argue that GPT-4's above-average performance is not necessarily evidence of "reasoning". That is, GPT-4 has no "understanding" but it has formidable reading speed and retention (memory).

While preparation for the above exams depends heavily on memorisation, other exams may focus more on reasoning and understanding.

Surely GPT-4 would fail some exams. But when it comes to GPT-4's exam performance, only the positive results are reported.

https://freeman.vc/notes/reasoning-vs-memorization-in-llms

◧◩
2. romwel+Bo2[view] [source] 2024-03-02 02:11:22
>>1vuio0+vn2
>Surely GPT-4 would fail some exams

Some? It does hilariously badly on basic math.

With confidence, though.

◧◩◪
3. ethbr1+Fp2[view] [source] 2024-03-02 02:26:03
>>romwel+Bo2
> hilariously badly on basic math. With confidence, though

How does it do on the GMAT? Sounds like a good candidate for an MBA program.

◧◩◪◨
4. tim333+pt3[view] [source] 2024-03-02 15:49:18
>>ethbr1+Fp2
Scored 680 / 800 in this try in March 23 https://www.linkedin.com/pulse/today-i-put-chatgpt-4-test-ha...

Update GTP-4 turbo is now up to about 770 beating most humans https://twitter.com/airesearchtools/status/17569731696325880...

[go to top]