HN user

poopbutt7

27 karma
Posts0
Comments30
View on HN
No posts found.
Nick Cave on ChatGPT and the creative process 3 years ago

There was a time in history where you COULD create real art and make a decent living out of it.

Honest question, is that actually true? Historically, professional art always struck me as the domain of the rich, the starving artist, or the person taking commissions for the rich.

0ThreadHN
Bye, Gemini 3 years ago

Gemini felt to me like the web's quiet cabin on a lake. I'd view through a terminal emulator on a Mac Classic.

The lack of infinite content makes it peaceful and manageable. The lack of search (or maybe it exists and I just didn't care to find it) makes finding little haunts and communities more rewarding.

It's just some personal blogs about synthesizers or cereal recipes- but it's genuine and not people trying to build a brand. No one is trying to sell you anything. It's felt totally uncorrupted.

0ThreadHN
Bard is getting better at logic and reasoning 3 years ago

Not sure I follow- the answer matches minus the first leading zeros. Change the range from 0-32, and it matches exactly. So it pretty clearly recognized the pattern and produced working code.

This question is a pretty obscure benchmark. Another commenter has it just printing the string, as suggested.

If there's some weird math trick to get an optimal implementation, it's probably beyond the grasp of nearly all actual people.

0ThreadHN
Bard is getting better at logic and reasoning 3 years ago

If you clarify the prompt a little (I used Write a python script that can produce this pattern:), GPT-4 gave me this:

To generate the given pattern, we need to identify the structure. After analyzing, it seems that the pattern follows a certain structure where the binary representation of each number from 1 to 15 is preceded by a certain number of zeroes. Here's a python script to generate such a pattern:

    def generate_pattern():
        pattern = ""
        for i in range(1, 16):
            # Convert i to binary and remove the "0b" prefix.
            binary = bin(i)[2:]
            # Number of zeroes to add before each binary.
            zeroes = 5 - len(binary)
            # Add binary to pattern with zeroes.
            pattern += "0" \* zeroes + binary
        return pattern

    print(generate_pattern())
The script starts by iterating through numbers from 1 to 15. For each number, it converts the number to a binary string and removes the "0b" prefix that Python adds by default. It calculates the number of zeroes to add before the binary string to maintain a fixed width of 5 characters, and then adds the binary string to the pattern with the preceding zeroes. Finally, it returns the complete pattern.

Which outputs: 000010001000011001000010100110001110100001001010100101101100011010111001111

It's missing the first set of zero's, but matches otherwise.

So, I guess it's AGI then.

0ThreadHN
Ask HN: ChatGPT et al. and NPCs 3 years ago

LLMs are- literally and figuratively- opening a lot of doors in robotics right now. In the sense that LLMs can provide mostly usable code, with a few prompts or some fine tuning can translate text commands into fairly primitive robot commands.

SayCan is one I've seen: https://say-can.github.io/

Using an LLM map a conversation into discrete, real in-world states changes or actions seems pretty similar.

0ThreadHN
US Department of Energy: Fusion Ignition Achieved 4 years ago

You are correct: this is the important point. Until this is actually powering homes at scale and competitive price- which, clearly from these numbers is a fantasy- developments in this field should be dismissed. It's embarrassing to see HN so excited about what's really quite the failure.

(Sent from my ENIAC)

0ThreadHN