71–80 of 217 posts
Earlier quoted context omitted.
At https://reviewr.ai we're using GPT-3 to summarize product reviews into simple bullet-point lists. Here's an example with backpack reviews: https://baqpa.com
Did you test it against extractive summarizers?
Earlier quoted context omitted.
Have you heard of GitHub copilot ? It’s based on GPT3 and I can tell you one thing: it does not generate meaningless prose (90% of the time)
The fact that GPT3 works at all for coding indicates that our programming languages are too low level and force a lot of redundancy (low entropy). From a programmer productivity optimization perspective it should be impossible to reliably predict the next statement. Of course there might be trade offs. Some of that redundancy might be helping maintenance programmers to understand the code.
Why? 99.9% of programming being done is composition of trivial logical propositions, in some semantic context. The things we implement are trivial, unless you're thinking about symbolic proofs etc
Earlier quoted context omitted.
Have you heard of GitHub copilot ? It’s based on GPT3 and I can tell you one thing: it does not generate meaningless prose (90% of the time)
The fact that GPT3 works at all for coding indicates that our programming languages are too low level and force a lot of redundancy (low entropy). From a programmer productivity optimization perspective it should be impossible to reliably predict the next statement. Of course there might be trade offs. Some of that redundancy might be helping maintenance programmers to understand the code.
Earlier quoted context omitted.
Have you heard of GitHub copilot ? It’s based on GPT3 and I can tell you one thing: it does not generate meaningless prose (90% of the time)
The fact that GPT3 works at all for coding indicates that our programming languages are too low level and force a lot of redundancy (low entropy). From a programmer productivity optimization perspective it should be impossible to reliably predict the next statement. Of course there might be trade offs. Some of that redundancy might be helping maintenance programmers to understand the code.
Earlier quoted context omitted.
The fact that GPT3 works at all for coding indicates that our programming languages are too low level and force a lot of redundancy (low entropy). From a programmer productivity optimization perspective it should be impossible to reliably predict the next statement. Of course there might be trade offs. Some of that redundancy might be helping maintenance programmers to understand the code.
>From a programmer productivity optimization perspective it should be impossible to reliably predict the next statement Why? 99.9% of programming being done is composition of trivial logical propositions, in some semantic context. The things we implement are trivial, unless you're thinking about symbolic proofs etc
Earlier quoted context omitted.
The fact that GPT3 works at all for coding indicates that our programming languages are too low level and force a lot of redundancy (low entropy). From a programmer productivity optimization perspective it should be impossible to reliably predict the next statement. Of course there might be trade offs. Some of that redundancy might be helping maintenance programmers to understand the code.
That would only follow if we were trying to optimize code for brevity, and I have no clue why that would be your top priority.
People were blaming cryptocurrencies miners for the prices of GPUs, when in fact it was the AI researchers who bought all the GPUs. :D I wonder what if somebody designs an electronic currency rewarded as payment for general GPU computations instead of just computing hashes? You pay some $, to train your model and the miner gets some coins. Every one is happy, electricity is not wasted and the GPUs gets used for a rea…
The current way of training is efficient when compute is located in a single place and is colocated with large quantities of training data. Distributing small parts of computation to remote computers is theoretically possible (and an active direction of research) but currently not preferable nor widely used; you really need very high bandwidth between all the nodes to constantly synchronize the hundreds-of-gigabytes…
Earlier quoted context omitted.
Have you heard of GitHub copilot ? It’s based on GPT3 and I can tell you one thing: it does not generate meaningless prose (90% of the time)
The fact that GPT3 works at all for coding indicates that our programming languages are too low level and force a lot of redundancy (low entropy). From a programmer productivity optimization perspective it should be impossible to reliably predict the next statement. Of course there might be trade offs. Some of that redundancy might be helping maintenance programmers to understand the code.
> The fact that GPT3 works at all for English indicates that English is too low level and forces a lot of redundancy (low entropy).
I don't think the goal is to compress information/language and maximize "surprise".
Earlier quoted context omitted.
Have you heard of GitHub copilot ? It’s based on GPT3 and I can tell you one thing: it does not generate meaningless prose (90% of the time)
The fact that GPT3 works at all for coding indicates that our programming languages are too low level and force a lot of redundancy (low entropy). From a programmer productivity optimization perspective it should be impossible to reliably predict the next statement. Of course there might be trade offs. Some of that redundancy might be helping maintenance programmers to understand the code.
Can anyone tell me what the value of GPT-3 actually is other than generating meaningless prose? What would a business use it for
At https://reviewr.ai we're using GPT-3 to summarize product reviews into simple bullet-point lists. Here's an example with backpack reviews: https://baqpa.com