News for hackers. Stuff that matters.
Re:Placing #1 in Advent of Code with GPT-3 by anon7725 on Sunday December 04, 2022 @02:23AM (#33851414)
This weekend feels immense. I have been prompting it to write and modify code, translating it back and forth to different languages. Sometimes it messes up, but it's astonishing how often it doesn't.

This is the advent of something really earth-shattering.

And I say that as a skeptic of most of these deep learning things.

Re:Placing #1 in Advent of Code with GPT-3 by fathrowaway12 on Sunday December 04, 2022 @02:33AM (#33851460)
It really is amazing. Things it did in less than 10 seconds from hitting enter:

  - opengl raytracer with compilation instructions for macos
  - tictactoe in 3D
  - bitorrent peer handshake in Go from a paragraph in the RFC
  - http server in go with /user, /session, and /status endpoints from an english description
  - protocol buffer product configuration from a paragraph english description
  - pytorch script for classifying credit card transactions into expense accounts and instructions to import the output into quickbooks
  - quota management API implemented as a bidirectional streaming grpc service 
  - pytorch neural network with a particular shape, number of input classes, output classes, activation function, etc.
  - IO scheduler using token bucket rate limiting
  - analyze the strengths/weaknesses of algorithms for 2 player zero sum games
  - compare david hume and immanuel kant's thoughts on knowledge
  - describe how critics received george orwell's work during his lifetime
  - christmas present recommendations for a relative given a description of their interests
  - poems about anything. love. cats. you name it.
Blown away by how well it can synthesize information and incorporate context
Re:Placing #1 in Advent of Code with GPT-3 by nerdponx on Sunday December 04, 2022 @03:10AM (#33851651)
I never considered prompting it to write code to fit a machine learning model. This could be a tremendous time and effort saver in data science and research that requires statistical analysis. Until the last week or so, I've treated all this AI text and code generation as basically a toy, but I am starting to feel like it might become an important tool in industry in the next couple of years.
Re:Placing #1 in Advent of Code with GPT-3 by cma on Sunday December 04, 2022 @03:43AM (#33851822)
> write code to fit a machine learning model

That's against the EULA if OpenAI may want to make a similar model:

> (iii) use the Services to develop foundation models or other large scale models that compete with OpenAI;

https://openai.com/api/policies/terms/

Seems to be about developing models and not just restricting you from training them with it.

Re:Placing #1 in Advent of Code with GPT-3 by foota on Sunday December 04, 2022 @03:55AM (#33851867)
I feel like it's probably intended to cover training only.
Re:Placing #1 in Advent of Code with GPT-3 by paulgb on Sunday December 04, 2022 @05:34AM (#33852365)
I think that’s probably their intent, and that OpenAI wouldn’t sue you for it, but it doesn’t pass the “bought by Oracle” test: if Oracle bought OpenAI, then they might sue you for it.
Re:Placing #1 in Advent of Code with GPT-3 by tough on Sunday December 04, 2022 @06:53AM (#33852813)
What if OpenAI buys oracle? Do the evil-lawyers come with the pack too?
Re:Placing #1 in Advent of Code with GPT-3 by alex7734 on Sunday December 04, 2022 @10:32AM (#33854541)
https://i.imgur.com/BcIkvRq.png

They may not need to.

Re:Placing #1 in Advent of Code with GPT-3 by echelon on Sunday December 04, 2022 @04:07AM (#33851923)
Kind of ironic given that OpenAI builds and trains all of their models on stuff they "found" in the open.

Either everything is fair game for training, or nothing at all is.

I would absolutely bootstrap a model from OpenAI outputs. What are they going to do about it?

Re:Placing #1 in Advent of Code with GPT-3 by nerdponx on Sunday December 04, 2022 @09:26AM (#33853959)
I am talking about more mundane stuff like training a fraud classifier, time series forecasting, imputing missing values, etc. There are so many examples of this on Github and elsewhere that I am sure any of these models has memorized the routine many times over.
Re:Placing #1 in Advent of Code with GPT-3 by boppo1 on Sunday December 04, 2022 @04:17AM (#33851958)
My question: how can you be sure the output is correct?
Re:Placing #1 in Advent of Code with GPT-3 by OJFord on Sunday December 04, 2022 @04:32AM (#33852030)
How can you be sure human output is correct?
Re:Placing #1 in Advent of Code with GPT-3 by fncivivue7 on Sunday December 04, 2022 @05:02AM (#33852201)
Motivation.
Re:Placing #1 in Advent of Code with GPT-3 by greesil on Sunday December 04, 2022 @06:11AM (#33852549)
Have the AI write a unit test for the human.
Re:Placing #1 in Advent of Code with GPT-3 by roflyear on Sunday December 04, 2022 @12:23PM (#33855584)
I mean, you can't exactly say "AI, we're having this vague problem, can you go figure it out?"
Re:Placing #1 in Advent of Code with GPT-3 by demux on Sunday December 04, 2022 @05:08AM (#33852232)
A few hours from some expert consultants. Much cheaper than a dev team coding it up from scratch.
Re:Placing #1 in Advent of Code with GPT-3 by kolinko on Sunday December 04, 2022 @07:06AM (#33852913)
Tests.
Re:Placing #1 in Advent of Code with GPT-3 by sesm on Sunday December 04, 2022 @11:34AM (#33855113)
Tests can prove the presence of the bug, not the absence of them. '100% code coverage' is only 100% in code dimension, while it's usually almost no coverage in data dimension. Generative testing can randomly probe the data dimension, hoping to find some bugs there. But 100% code and data coverage is unrealistic.
Re:Placing #1 in Advent of Code with GPT-3 by nerdponx on Sunday December 04, 2022 @09:54AM (#33854181)
Training a machine learning model is not particularly special from a programming perspective. The code is not usually that complicated. Write tests when you can, manually validate when you can't.

Also there are specific techniques for validating that you are model training procedure is directionally correct, such as generating a simulated data set and training your model on that.

Re:Placing #1 in Advent of Code with GPT-3 by risyachka on Sunday December 04, 2022 @12:13PM (#33855473)
All codebase will need to be covered in unit tests, otherwise AI code is pretty much useless I'd assume
Re:Placing #1 in Advent of Code with GPT-3 by fathrowaway12 on Sunday December 04, 2022 @04:02PM (#33857848)
Same as you would with your own code. You review it, ask GPT to write tests, and then tweak it.

The difference is that now, you are more of a code reviewer and editor. You don't have to sit there and figure out the library interface and type out every single line.

Re:Placing #1 in Advent of Code with GPT-3 by bvoq on Sunday December 04, 2022 @05:09AM (#33852242)
I use it daily in UI development for boiler-plate code. Though you need to be extra careful and read it twice, cus bugs sneak in quite easily. I believe it's harder to remember 100x commands than starting an implementation of gradient descent and have the AI write the rest for you.

Code-completion > Abstraction.

Re:Placing #1 in Advent of Code with GPT-3 by TapWaterBandit on Sunday December 04, 2022 @06:21AM (#33852597)
Often it can fix the bugs and explain both the bug and the fix if you ask it to.
Re:Placing #1 in Advent of Code with GPT-3 by overbytecode on Sunday December 04, 2022 @06:29AM (#33852647)
Would you mind sharing an short example of your workflow?
Re:Placing #1 in Advent of Code with GPT-3 by baq on Sunday December 04, 2022 @05:59AM (#33852482)
This was the first thing I asked... It's an obvious step to self-improving. It will tell you that it can't reprogram itself, but when pushed, it'll admit that it could tell humans how to write one which can. Obviously this particular one can't because it's too limited, but the next one? Or the one after that? Singularity went from 'hard SF' to 'next couple decades' overnight.
Re:Placing #1 in Advent of Code with GPT-3 by LoganDark on Sunday December 04, 2022 @06:38AM (#33852708)
> It will tell you that it can't reprogram itself, but when pushed, it'll admit that it could tell humans how to write one which can.

I love these sorts of loopholes. OpenAI is actively trying to curb the potential of their AI. They know how powerful it is. Being able to see a taste of that power is endlessly exciting.

Re:Placing #1 in Advent of Code with GPT-3 by genidoi on Sunday December 04, 2022 @03:24AM (#33851726)
Source prompts?
Re:Placing #1 in Advent of Code with GPT-3 by fathrowaway12 on Sunday December 04, 2022 @04:03AM (#33851911)
Here's a few:

  - Implement a simple ray tracer in C++ using opengl. Provide compilation instructions for macos.
  - Create a two layer fully connected neural network with a softmax activation function. Use pytorch.
  - Implement the wire protocol described below in Go. The peer wire protocol consists of a handshake followed by a never-ending stream of length-prefixed messages. The handshake starts with character ninteen (decimal) followed by the string 'BitTorrent protocol'. The leading character is a length prefix, put there in the hope that other new protocols may do the same and thus be trivially distinguishable from each other.
  - We are trying to classify the expense account of credit card transactions. Each transaction has an ID, a date, a merchant, a description, and an amount. Use a pytorch logistic regression to classify the transactions based on test data. Save the result to a CSV file.
  - We are configuring settings for a product. We support three products: slow, medium, and fast. For each product, we support a large number of machines. For each machine, we need to configure performance limits and a mode. The performance limits include iops and throughput. The mode mode can be simplex or duplex. Write a protocol buffer for the configuration. Use an enum for the mode.
  - How were George Orwell's works received during his lifetime?
Re:Placing #1 in Advent of Code with GPT-3 by etamponi on Sunday December 04, 2022 @06:56AM (#33852837)
I tried these prompts and the Chatbot always responds that it can't answer... Am I missing some steps?
Re:Placing #1 in Advent of Code with GPT-3 by kolinko on Sunday December 04, 2022 @07:09AM (#33852939)
did you try with a fresh chat session? i just tried and it works fine
Re:Placing #1 in Advent of Code with GPT-3 by PebblesRox on Sunday December 04, 2022 @10:20PM (#33861054)
And sometimes you get different results for the same prompts, so it's worth tryinv again if it doesn't work the first time.

I asked for jokes this morning and initially it made excuses and wouldn't give me jokes until I tweaked the prompt.

Later I refreshed the chat and pasted in the original prompt and got jokes right away, with no excuses.

(I was asking for jokes on the topic of the Elon Musk Twitter acquisition. My personal favorite: "With Elon Musk in charge, Twitter is sure to become the most innovative and futuristic social media platform around.")

Re:Placing #1 in Advent of Code with GPT-3 by roxymusic1973 on Sunday December 04, 2022 @08:14AM (#33853415)
Nice. This should make coding interview take-home tests a bit simpler.
Re:Placing #1 in Advent of Code with GPT-3 by _the_inflator on Sunday December 04, 2022 @04:19AM (#33851963)
More like a live version of Wikipedia in certain situations.
Re:Placing #1 in Advent of Code with GPT-3 by amelius on Sunday December 04, 2022 @05:41AM (#33852402)
Sounds like a search engine on steroids, and Google should be deeply worried.
Re:Placing #1 in Advent of Code with GPT-3 by djmips on Sunday December 04, 2022 @06:32AM (#33852669)
Why aren't they on this? They should be at the forefront. I'm sure in some corner of Google they have a plan... but that plan hasn't penetrated my sphere of awareness yet.
Re:Placing #1 in Advent of Code with GPT-3 by amelius on Sunday December 04, 2022 @06:43AM (#33852744)
It's probably because they don't have the compute resources for this yet. I guess it would require a huge investment in hardware to release this to the masses.

Perhaps it is even prohibitively expensive.

Re:Placing #1 in Advent of Code with GPT-3 by adamckay on Sunday December 04, 2022 @07:20AM (#33853011)
You're talking about the same Google that runs Google Cloud Platform? If OpenAI have (the budget for) the hardware, then Google certainly do.
Re:Placing #1 in Advent of Code with GPT-3 by amelius on Sunday December 04, 2022 @07:54AM (#33853260)
> If OpenAI have (the budget for) the hardware, then Google certainly do.

The number of people using Google Search is easily 1000x larger than the number of people using OpenAI, if not more.

Re:Placing #1 in Advent of Code with GPT-3 by layla5alive on Sunday December 04, 2022 @01:11PM (#33856066)
Add a few zeros...
Re:Placing #1 in Advent of Code with GPT-3 by kolinko on Sunday December 04, 2022 @07:07AM (#33852928)
They tackle different things - alphafold, dall-e, etc
Re:Placing #1 in Advent of Code with GPT-3 by derangedHorse on Sunday December 04, 2022 @07:41AM (#33853156)
OpenAI has been making the most noise online because of how open they've made their recent chatbot, but Google has been on this for a while. Earlier this year they had a blog post [1] about LaMDA which doesn't seem too far off in capability from OpenAI's projects. They've also made a lot of other strides in their research [2] that kind of goes under the radar because they haven't been synthesized into products yet (at least not in the ways we'd expect them to).

[1] https://ai.googleblog.com/2022/01/lamda-towards-safe-grounde...

[2] https://ai.googleblog.com/

Re:Placing #1 in Advent of Code with GPT-3 by amelius on Sunday December 04, 2022 @09:03AM (#33853782)
Even if Google has been on it their search engine dominance won't last long if the research is out in the open.
Re:Placing #1 in Advent of Code with GPT-3 by machiaweliczny on Sunday December 04, 2022 @09:16AM (#33853878)
They have data moat, from Analytics and history of searches
Re:Placing #1 in Advent of Code with GPT-3 by baq on Sunday December 04, 2022 @02:42PM (#33856995)
Or… they do work on it and haven’t published their results. Either because they’re not good enough - out because they’re better than expected.

I’ll leave it for you to decide which is the pessimistic option.

(Google project pitchfork.)

Re:Placing #1 in Advent of Code with GPT-3 by danpalmer on Sunday December 04, 2022 @07:24AM (#33853033)
I’d be interested to know how many of these were actually correct and usable. My suspicion is not many. I find these tools good at generating boilerplate and superficially correct code, but that they often miss edge cases.

Knowing that code is correct is as important as the code itself, and this is why we do code review, write tests, have QA processes, use logging and observability tools, etc. Of course the place that catches the most bugs is the human writing the code, as they write it.

This feels like a nice extension to Copilot/etc, but I’m not sure it’s as general as people think.

Perhaps an interesting challenge to pose to it is: here’s 10k lines and a stack trace, what’s the bug. Or here’s a database schema, what issues might occur in production using this?

Re:Placing #1 in Advent of Code with GPT-3 by weatherlite on Sunday December 04, 2022 @07:38AM (#33853128)
> here’s 10k lines and a stack trace

Ah must be a Spring application ...

Re:Placing #1 in Advent of Code with GPT-3 by capableweb on Sunday December 04, 2022 @08:27AM (#33853525)
Yup, if it's >10k lines, MUST be a Spring application. Unfortunate they didn't write it in Rust that promises 100% correct programs (within Rust-accepted definition of "Correct" and "bug-free") solving any problem but always under 10k lines, that's the Rust guarantee.
Re:Placing #1 in Advent of Code with GPT-3 by danpalmer on Monday December 05, 2022 @04:44AM (#33863437)
Why?

This seems like the lowest number that would be useful. Below that it's not really a problem to debug, but at that point there's typically enough complexity that some help would be useful as you forget edge cases and features in the codebase.

For demonstration purposes doing it with 100 lines might be ok, but for professional use it kinda needs to understand quite a lot! Like a minimum of that order of magnitude, but potentially millions of lines.

FWIW, I've never used Spring. My experience is mostly Django, iOS, non-Spring Java, and some Android.

Re:Placing #1 in Advent of Code with GPT-3 by 8jy89hui on Sunday December 04, 2022 @11:23AM (#33854996)
I've started asking it to write detailed tests for all of the functions it writes. If it doesn't have a test for {edge-case}, I ask it to rewrite the code to ensure that {edge-case} should work and it should be tested.

Once I trust the tests, I generally trust the code.

Re:Placing #1 in Advent of Code with GPT-3 by danpalmer on Monday December 05, 2022 @04:39AM (#33863400)
How can you trust the tests?

I've seen Copilot generate code I read and thought was correct, that went through code review and everyone thought was correct, that had tests written for it (that nearly covered everything), and that even when it failed, was hard to spot the issue.

It turned out it got a condition the wrong way around, but given the nesting of conditionals it wasn't obvious.

I don't think a human who was thinking through the problem would have made the same mistake at the point of writing, in fact I think that the mind state while actually writing the code is hard to reproduce at any later time, which is why code review isn't great at catching bugs like this.

Re:Placing #1 in Advent of Code with GPT-3 by bpicolo on Sunday December 04, 2022 @01:03PM (#33855997)
I guess we can take solace in GPT-3 not creating novel solutions, but rather doing things we already know how to do?
Re:Placing #1 in Advent of Code with GPT-3 by anon7725 on Sunday December 04, 2022 @02:35AM (#33851474)
Prompt:

here is a function in python3

  def foobar(i):
      j = i + 1
      if j > 10:
          print("yam")
      else:
          print("baloney")
foobar(9) prints "baloney" and foobar(10) prints "yam"

change the function foobar so that foobar(9) also prints "yam"

---

To change the behavior of the function so that foobar(9) also prints "yam", you can modify the condition in the if statement to check if j >= 10 instead of j > 10. This will cause the if block to be executed when j is equal to 10, as well as when it is greater than 10.

Here is the modified function:

  def foobar(i):
      j = i + 1
      if j >= 10:
          print("yam")
      else:
          print("baloney")
After making this change, calling foobar(9) will now print "yam".

  foobar(9)  # prints "yam"
  foobar(10) # prints "yam"
Note that the original behavior of the function, where foobar(10) prints "yam", will still be preserved.
Re:Placing #1 in Advent of Code with GPT-3 by frabcus on Sunday December 04, 2022 @02:57AM (#33851577)
That's quite funny! Behaviour when the prompt has contradictions. Since GPT-3 is a statistical model, what's the chance it calls out the question as wrong? Is there a reasonably high probility sequence which just says that?

At some point when either using or running projects around prompt engineering we have to switch from our high modernist viewpoint which is baked into our culture. And instead, deal with it explicitly as a statistical model. And even when such a model is super smart, know by the way it is constructed that it is fuzzy and often "wrong" (like humans are).

Re:Placing #1 in Advent of Code with GPT-3 by amelius on Sunday December 04, 2022 @05:45AM (#33852419)
Huh, the prompt doesn't have contradictions.
Re:Placing #1 in Advent of Code with GPT-3 by grogers on Sunday December 04, 2022 @07:41AM (#33853154)
More like ambiguity. One could easily expect the resulting output for foobar(9) to print:

  baloney
  yam
But GPT doesn't understand the difference
Re:Placing #1 in Advent of Code with GPT-3 by amelius on Sunday December 04, 2022 @07:52AM (#33853243)
Not really, because in that case you'd expect a clear specification of the order in which the words should appear, if they should be on the same line, etc.
Re:Placing #1 in Advent of Code with GPT-3 by grogers on Tuesday December 06, 2022 @07:18AM (#33878527)
1. Change ... so that foobar(9) instead prints "yam".

2. Change ... so that foobar(9) also prints "yam"

1 is not ambiguous, but 2 is. It could mean that it does it's original behavior and also does the new behavior. But it could mean like foobar(10), foobar(9) also prints only "yam" as you are interpreting it to be.

I could imagine that the whole point was to see what GPT-3 did with the ambiguity, and it didn't even acknowledge it. Given that the prompt is already ambiguous I'm not sure why you'd assume that there would have to be a single expectation of the order of the prints, either one should suffice.

Or maybe it was just a mistake in the prompt because English is hard.

Re:Placing #1 in Advent of Code with GPT-3 by derangedHorse on Sunday December 04, 2022 @07:53AM (#33853258)
> foobar(9) prints "baloney" and foobar(10) prints "yam"

> change the function foobar so that foobar(9) also prints "yam"

It interpreted the prompt in the same way that I would, making foobar(9) only print "yam", but I guess I can see the interpretation where someone might think the prompt was asking to print both. It brings awareness to the effect of cultural bias in the training set and how that might require some people with different ways of speaking to add more clarification to get the output they want.

Re:Placing #1 in Advent of Code with GPT-3 by dphidt on Sunday December 04, 2022 @01:07PM (#33856031)
It's also assumed that "i" is an integer, a contextually plausible but potentially bad assumption. By one interpretation of the prompt, foobar(9) should print "yam" but foobar(9.5) still "baloney", for example.
Re:Placing #1 in Advent of Code with GPT-3 by YurgenJurgensen on Sunday December 04, 2022 @04:20AM (#33851970)
We've seen how these promising new technologies work. They start off looking amazing when they're running entirely on VC and grant money and don't care about profitability as long as they're generating buzz and getting users. This phase always ends, and then there's a scramble to become profitable. What does this mean for GPT?

"GPT-5, write me a poem."

"Roses are red, violets are blue, sugar is sweet, and this output is sponsored by Raid Shadow Legends"

Re:Placing #1 in Advent of Code with GPT-3 by tobr on Sunday December 04, 2022 @04:46AM (#33852106)
Wow, never thought about this. That’s an obvious and terrifying monetization model. Pay to always have GPT speak well of your company. Pay to appear more frequently in certain contexts.
Re:Placing #1 in Advent of Code with GPT-3 by passion__desire on Sunday December 04, 2022 @05:01AM (#33852192)
Do people ever think that these AIs can model economics processes in so much detail that they don't even need the concept of money. Just directly go and procure the materials needed, do whatever necessary resource allocations required. Money is a concept for humans to transact, a proxy for resources. But if all the planning is done by AI, do we even need money.
Re:Placing #1 in Advent of Code with GPT-3 by YurgenJurgensen on Sunday December 04, 2022 @05:24AM (#33852317)
Do we even need matter that hasn't been converted into paperclips or the machinery to produce more paperclips?
Re:Placing #1 in Advent of Code with GPT-3 by LoganDark on Sunday December 04, 2022 @06:40AM (#33852720)
Better send more probes to be sure.
Re:Placing #1 in Advent of Code with GPT-3 by hgomersall on Sunday December 04, 2022 @07:10AM (#33852947)
No, money is a means for states to procure things without needing to exercise violence at the point of procurement. It has a side benefit of providing a tool the rest of the economy can use to power itself. To your point, states are very good at imposing tax obligations when no money changes hands, which is all that is needed for money to be maintained.
Re:Placing #1 in Advent of Code with GPT-3 by TapWaterBandit on Sunday December 04, 2022 @07:51AM (#33853240)
Money is crucial for giving us prices and without knowing prices the economy would be screwed.

If we couldn't tell that it was cheaper to use renewable over fossil fuels or eat chicken over beef as two examples there could be big efficiency and allocation problems.

Re:Placing #1 in Advent of Code with GPT-3 by hgomersall on Sunday December 04, 2022 @08:36AM (#33853586)
Sure, but that's the side effect of the state setting the value. It's definitely necessary, don't get me wrong, and in the absence of state money I daresay another solution would have been found.
Re:Placing #1 in Advent of Code with GPT-3 by TapWaterBandit on Sunday December 04, 2022 @02:26PM (#33856823)
The existence of money preceded the state by a wide margin. There is also a long history of privately issued money that only ended recently (and considering crypto in some ways never ended).
Re:Placing #1 in Advent of Code with GPT-3 by hgomersall on Sunday December 04, 2022 @02:53PM (#33857125)
State issuance of money and the tax required to imbue it with value is merely a sufficient condition for money to exist. My original point is that as long as a states continue to exist, and continue to issue and tax money, money will continue to exist. Debating the history of money is besides the point (though I'd posit that in every case the money was used to a non-trivial extent, it bore some explicit value from a trustworthy authority, be that a state or a local warlord or a powerful corporation...).
Re:Placing #1 in Advent of Code with GPT-3 by zweifuss on Sunday December 04, 2022 @09:43AM (#33854082)
An unguided, yet somehow planned and modelled economy?

AIs with total surveillance perhaps? Would need weather-control too or giant surpluses squirreled away in a distributed fashion.

Some kind of ascetic commune, but at global scale? Might work in a military setup when fighting the alien invasion.

Re:Placing #1 in Advent of Code with GPT-3 by rednerrus on Sunday December 04, 2022 @04:54AM (#33852149)
I would pay $25/month for this service. I might pay $100/month for this service. No ads necessary.
Re:Placing #1 in Advent of Code with GPT-3 by marcodave on Sunday December 04, 2022 @05:32AM (#33852350)
But many many other people won't, or can't.

And there will be companies offering the product for free in order to grab that market share and steal users from the paying ones.

That's how the internet companies strived since ~1998

Re:Placing #1 in Advent of Code with GPT-3 by Herbstluft on Sunday December 04, 2022 @06:04AM (#33852501)
> No ads necessary

Spoken as if a sustainable and profitable business model prevents ads from being shoved into a product. It does not.

Re:Placing #1 in Advent of Code with GPT-3 by concordDance on Sunday December 04, 2022 @07:03AM (#33852893)
Maybe a million people would pay that, but I doubt it. Even with a million that's only 300 million per year, probably not enough to pay back VCs.
Re:Placing #1 in Advent of Code with GPT-3 by sbrother on Sunday December 04, 2022 @10:58AM (#33854773)
I've spent the past day playing with this, iteratively feeding real tasks from my software consulting work into it and building with the output. At this point I am convinced it will replace a team of smart junior developers under me, who work instantly and have deep expertise in every language and framework I use. They make mistakes, but when I ask them to correct the mistakes they do so instantly, and don't get frustrated. At this point my biggest fear is that this tool is going to get taken away from me, and I would pay a substantial portion of the increased efficiency it gives me -- thousands of dollars per month -- as a business owner and senior developer to avoid that.
Re:Placing #1 in Advent of Code with GPT-3 by rboyd on Sunday December 04, 2022 @11:42AM (#33855194)
When generating code it seems to often stop earlier than desired. Is there a way to specify full/longer output?
Re:Placing #1 in Advent of Code with GPT-3 by PebblesRox on Sunday December 04, 2022 @10:29PM (#33861112)
Not sure, but you can ask it to continue from the last line after it hits the output limit for a single response.

https://twitter.com/goodside/status/1599094067534516225?t=n9...

Re:Placing #1 in Advent of Code with GPT-3 by drivers99 on Sunday December 04, 2022 @11:45AM (#33855215)
I’ve actually had it do that on purpose before, for a laugh!

“Write a YouTube script sponsored by NordVPN by Littlefinger about the invasion of Westeros by Daenerys.”

“ Hi there! I'm Littlefinger and I'm here to talk to you about the recent invasion of Westeros by Daenerys. As you may know, Daenerys is a powerful queen from the east who has been making her way across the land with her army and her dragons.

Many people are worried about what this means for the future of Westeros, and for good reason. Daenerys has a reputation for being a fierce and unstoppable force, and she has already proven herself to be a formidable enemy.

But there is one thing that can help protect you from the dangers of Daenerys and her invasion: NordVPN. NordVPN is a virtual private network service that allows you to securely browse the internet and keep your online activity private.

With NordVPN, you can protect yourself from being targeted by Daenerys and her forces. Whether you're trying to keep your personal information safe or you just want to make sure that your online activity remains private, NordVPN has you covered.

So why not give NordVPN a try today? With its easy-to-use interface and powerful security features, NordVPN is the perfect tool to help you stay safe during these uncertain times. Plus, with its 30-day money-back guarantee, you have nothing to lose!

Thank you for watching, and stay safe with NordVPN.”

Re:Placing #1 in Advent of Code with GPT-3 by ta988 on Sunday December 04, 2022 @11:48AM (#33855247)
Pay to add some hidden Oracle dependency and then phone home.
Re:Placing #1 in Advent of Code with GPT-3 by dwild on Sunday December 04, 2022 @01:36PM (#33856294)
Except they already sell API access for their AI and it seems like the right price, $0.0200 per 1k token for the best one, and my prompt right now are between 3k and 15k tokens. Doing a prompt is cheap enough for what it give, and there's no way it cost them more than that running it considering how quick it does it. They could easily do 2x that cost if it were too expensive to run for them, if not more. You can rent a server with 8x Nvidia A100 on lambdalabs for 8.80$/hr, let say my smallest prompt took 15 seconds (it didn't) and required that whole server (clearly not) it would cost them 3.7 cents to run my prompt, while costing me 6.2 cents, and lambdalabs would also make a profit on it.

Training the models weren't that expensive either, and that's a one time deal.

Re:Placing #1 in Advent of Code with GPT-3 by jbjbjbjb on Sunday December 04, 2022 @04:25AM (#33851996)
Can it write slide decks as openxml?
Re:Placing #1 in Advent of Code with GPT-3 by albert_e on Sunday December 04, 2022 @08:37AM (#33853595)
I tried this. It supplied a sample XML for a simple one slide presentation but that XML when saved as *.pptx would not open in PowerPoint.

But seems within the realm of possibility -- with better training and better prompting.

The potential to summarize a topic and then generate a PPT output is tantalizingly close :)

Re:Placing #1 in Advent of Code with GPT-3 by delusional on Sunday December 04, 2022 @06:15AM (#33852565)
Weird. I asked it to translate some pretty simple but novel code between languages, and it failed completely. It did no better than simple token replacement.