new gpt-4-april-24 vs. old gpt-4

test #1 → logical test.
test #2 → math problem-solving.
test #3 → write a poem in ABAB.

test #1 → logical test:

I asked both models to solve this:

'I have 2 apples, then I buy 2 more.

I bake a pie with 2 of the apples.

After eating…

new gpt-4-april-24 vs. old gpt-4

test #1 → logical test.
test #2 → math problem-solving.
test #3 → write a poem in ABAB.

test #1 → logical test:

I asked both models to solve this:

'I have 2 apples, then I buy 2 more.

I bake a pie with 2 of the apples.

After eating…

gemini 1.5 is out.

google claims it can 'watch & understand videos up to 1M token'.

I don't trust google:
→ so I made my own benchmark.

↓ Spoiler alert, gemini cannot do it:

google search feels like an endless ad.

So I ran 3 tests comparing google, chatgpt, perplexity & grok.

#1: 'how to write a founder agreement'