342
ChatGPT In Trouble: OpenAI may go bankrupt by 2024, AI bot costs company $700,000 every day
(www.firstpost.com)
this post was submitted on 13 Aug 2023
342 points (74.6% liked)
Technology
59323 readers
5183 users here now
This is a most excellent place for technology news and articles.
Our Rules
- Follow the lemmy.world rules.
- Only tech related content.
- Be excellent to each another!
- Mod approved content bots can post up to 10 articles per day.
- Threads asking for personal tech support may be deleted.
- Politics threads may be removed.
- No memes allowed as posts, OK to post as comments.
- Only approved bots from the list below, to ask if your bot can be added please contact us.
- Check for duplicates before posting, duplicates may be removed
Approved Bots
founded 1 year ago
MODERATORS
you are viewing a single comment's thread
view the rest of the comments
view the rest of the comments
If AI was so great, it would find a solution to operate at fraction of the cost it does now
Wait, has anybody bothered to ask AI how to fix itself? How much Avocado testing does it do? Can AI pull itself up by its own boot partition, or does it expect the administrator to just give it everything?
Really says something that none of your responses yet seem to have caught that this was a joke.
The upvotes vs comments shows the vocal minority is just doing vocal minority things.
if we don't know, it doesn't know.
If we know, but there's no public text about it, it doesn't know either.
it is trained off of stuff that has already been written, and trained to emulate the statistical properties of those words. It cannot and will not tell us anything new
I asked Bard how ChatGPT can fix itself, here's what it said:
ChatGPT can fix itself in a number of ways, including:
Retraining on a larger dataset. ChatGPT is trained on a massive dataset of text and code, but it can always be retrained on a larger dataset. This would help ChatGPT to learn new things and improve its performance.
Using a different algorithm. ChatGPT is currently trained using the GPT-3 algorithm, but there are other algorithms that could be used. For example, ChatGPT could be trained using the Megatron-Turing NLG algorithm, which is one of the most powerful language models in the world.
Using a combination of algorithms. ChatGPT could also be trained using a combination of algorithms. This would allow ChatGPT to benefit from the strengths of different algorithms.
Using a feedback loop. ChatGPT could be used to generate text, and then this text could be used to train ChatGPT. This would allow ChatGPT to learn from its own mistakes and improve its performance over time.
Using human feedback. ChatGPT could also be used to generate text, and then this text could be reviewed by humans. The human feedback could then be used to improve ChatGPT's performance.
"Using a feedback loop. ChatGPT could be used to generate text, and then this text could be used to train ChatGPT. This would allow ChatGPT to learn from its own mistakes and improve its performance over time."
So basically create its own Fox News and see how that goes.
this is widely known to very quickly destroy your model
Remember, this is Bard's advice for ChatGPT
The feedback loop is already happening, and is called model collapse.
It's not a good thing.
It's working on it. It's just a pretty difficult task to be better than 50 years of optimization by human computer scientists https://www.nature.com/articles/d41586-023-01883-4
Deepmind is actually working on an AI that improve performances of low level programs. It started with improving sorting algorithm.
It's an RL algorithm.
Main issue is that everything takes time, and expectations on current AI are artificially inflated.
It will reach the point most are discussing now, it'll simply take a bit longer than people expect
Source: https://www.nature.com/articles/d41586-023-01883-4