GPT-3 is no longer the only game in town • Hacker News Board

Re: GPT-3 is no longer the only game in town

#81

Post by robbedpeter » Sun, Nov 07, 2021, 6:23 PM UTC

iamcurious wrote: post #61

singlow wrote: post #53

Earlier quoted context omitted.

Isn't that just because others have stored solutions to these problems in GitHub?

That is my question too. Is it a fancier autocomplete? Or does it reason about code?

It reasons over the semantic network between tokens, in a feedforward inference pass over the 2k(ish) words or tokens of the prompt. Sometimes that reasoning is superficial and amounts to probabilistic linear relationships, but it can go deeply abstract depending on training material, runtime/inference parameters, and context of the prompt.

Re: GPT-3 is no longer the only game in town

#82

Post by Tenoke » Sun, Nov 07, 2021, 6:23 PM UTC

evergrande wrote: post #39

xyproto wrote: post #32

I think companies should be banned from having "Open" in their names.

OpenAI takes the Orwellian cake.

I hear a lot of low effort takes about OpenAI but how exactly is providing your service via a paid API the "Orwellian cake"? Is this really the most (or even at all) Orwellian practice for you?

Re: GPT-3 is no longer the only game in town

#83

Post by pharmakom » Sun, Nov 07, 2021, 6:23 PM UTC

crubier wrote: post #4

mrbukkake wrote: post #2

Can anyone tell me what the value of GPT-3 actually is other than generating meaningless prose? What would a business use it for

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)

Code is easier to write than read and maintain, so how useful is something that generates pages of 90% correct code?

Re: GPT-3 is no longer the only game in town

#84

Post by icelancer » Sun, Nov 07, 2021, 6:24 PM UTC

amelius wrote: post #6

crubier wrote: post #4

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)

How many % of the time does it produce code that compiles?

I was exceptionally skeptical about it, but it's been very useful for me and I'm only using it for minor tasks, like automatically writing loops to pull out data from arrays, merge them, sort information, make cURL calls and process data, etc.

Simply leading the horse to water is enough in something like PHP:

// instantiate cURL event from API URL, POST vars to it using key as variable name, store output in JSON array and pretty print to screen

Usually results in code that is 95-100% of the way done.

Re: GPT-3 is no longer the only game in town

#85

Post by icelancer » Sun, Nov 07, 2021, 6:25 PM UTC

crubier wrote: post #65

ilteris wrote: post #46

Earlier quoted context omitted.

I am so confused. Is there a tutorial explaining how you are using in the IDE whatever it is. I use vscode curious if it can be applied. Thanks

It works very well with VSCode. It has an integration. It shows differently than normal autocomplete, it shows just like gmail autocomplete (grayed out text sugggestion, and press tab to actually autocomplete). Sometimes the suggestion is just a couple tokens long, sometimes it’s an entire page of correct code. Nice trick: write a comment describing quickly what your code will do (“// order an item on click”) and enj…

Interesting second use case; I use comments like this already as typical practice and I agree Copilot fills in the gaps quite well - never thought to do it in reverse... will give that a shot today.

Re: GPT-3 is no longer the only game in town

#86

Post by Simon321 » Sun, Nov 07, 2021, 6:27 PM UTC

supperburg wrote: post #52

I have supported my beliefs on this topic in these threads to the point of exhausting myself. The tools that we use to find these agents are the underpinning of AGI, it’s coming way faster than even most people here appreciate, this development is intrinsically against the interest of human beings. Please stop and think, please.

I argue it's very much in the interest of human beings. It has been since we first picked up a rock and used it has a hammer. It's the ultimate tool and has the potential to bring unseen prosperity.

Re: GPT-3 is no longer the only game in town

#87

Post by CamperBob2 » Sun, Nov 07, 2021, 6:33 PM UTC

mrbukkake wrote: post #2

Can anyone tell me what the value of GPT-3 actually is other than generating meaningless prose? What would a business use it for

GPT-3 and similar ML/AI projects may have many interesting and valuable commercial applications, not all of which are readily apparent at this stage of the game. For instance, it could be used to insert advertisements for herbal Viagra at https://www.geth3r3a1N0W.com into otherwise-apropros comments on message boards, preferably near the end once it's too late to stop reading.

Life online is about to become very annoying.

Re: GPT-3 is no longer the only game in town

#88

Post by keithalewis » Sun, Nov 07, 2021, 6:34 PM UTC

qwertox wrote: post #47

If I were to run GPT-3 on my 70000 browser bookmarks, what kind of insights could I get from that? Only by analyzing the page title (from the bookmark, not by re-fetching the url) and eventually also the domain name.

print gpt.submit_request("Give me insights")

>>> You are spending way to much time browsing.

Re: GPT-3 is no longer the only game in town

#89

Post by kingcharles » Sun, Nov 07, 2021, 6:37 PM UTC

cma wrote: post #80

hubraumhugo wrote: post #62

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

How do you avoid libel?

Are you confusing libel with something else? Can you extrapolate what you mean here? Are you saying that they will be liable for libel (!) if they publish a negative summary of a product?

Re: GPT-3 is no longer the only game in town

#90

Post by robbedpeter » Sun, Nov 07, 2021, 6:37 PM UTC

vitus wrote: post #31

DeathArrow wrote: post #23

Earlier quoted context omitted.

>What would a business use it for If you think about business uses you can actually get advices from Jerome Powell, simulated by GPT-3. If someone use GPT-3 to simulate Warren Buffet, he can extract even more value. https://www.institutionalinvestor.com/article/b1tktmhcfdyqsk...

Somehow I don't think that this is quite how Jerome Powell would respond in an interview: > Interviewer: How do you think a global pandemic would impact the financial system? > Mr. Powell: A pandemic will have impact on the economy. It will have an impact on the financial system. > Interviewer: What would the impact be? > Mr. Powell: If a major pandemic occurred, the economy would be affected, and the financial syste…

This is a bad example. Here's an output from gpt-j-6b by EleutherAI: Prompt( Jerome Powell was interviewed about the impact of a pandemic on the economy.

> > Interviewer: What would the impact be? > Mr. Powell: If a major pandemic occurred)

Output( it could be very disruptive. > > Interviewer: How disruptive? > Mr. Powell: Well, it could be disruptive in a number of ways. > > Interviewer: How so? > Mr. Powell: Well, one of the first things that would be disrupted would be the supply chain. )

Using prompts well makes a huge difference.

If you parse the generated output, classify it, then develop a decision tree that uses further prompts to refine the response, you can get more sophisticated, valuable responses.

The output in the parent is comparable to an off-the-cuff interview response. If you emulate a deeper thought process, you can get more meaningful output, and if you use the right prompts, you can access the semantic networks in the model related to your domain of interest.