Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Grammarly is offering ‘expert’ AI reviews from famous dead and living writers

wired.com

Post reply on HN
Print view View original

81–90 of 214 posts

Re: Grammarly is offering ‘expert’ AI reviews from famous dead and living writers

#81

Post by inaros »

simianwords wrote: post #41
plewd wrote: post #37

Earlier quoted context omitted.

like OP originally said, the LLM doesn't have access to the actual process of the author, only the completed/refined output. Not sure why you need a concrete example to "test", but just think about the fact that the LLM has no idea how a writer brainstorms, re-iterates on their work, or even comes up with the ideas in the first place.

i don't buy this logic. if i have studied an author greatly i will be able to recognise patterns and be able to write like them. ex: i read a lot of shakespeare, understand patterns, understand where he came from, his biography and i will be able to write like him. why is it different for an LLM? i again don't get what the point is?

>> i again don't get what the point is?

The point is that you dont become Jimi Hendrix or Eric Clapton even if you spend 20 years playing on a cover band. You can play the style, sound like but you wont create their next album.

Not being Jimi Hendrix or Eric Clapton is the context you are missing. LLMs are Cover Bands...

Re: Grammarly is offering ‘expert’ AI reviews from famous dead and living writers

#82

Post by esafak »

Planktonne wrote: post #74
simianwords wrote: post #67

Earlier quoted context omitted.

Why do you say it has a different process? When I ask it to do integrals it uses the same process as me

Not everything works like integrals. Some things don't have a standard process that everyone follows the same way. Editing is one of these things. There can be lots of different processes, informed by lots of different things, and getting similar output is no guarantee of a similar process.

The process is irrelevant if the output is the same, because we never observe the process. I assume you are arguing that the outputs are not guaranteed to be the same unless you reproduce the process.

If we are talking about human artifacts, you never have reproducibility. The same person will behave differently from one moment to the next, one environment to another. But I assume you will call that natural variation. Can you say that models can't approximate the artifacts within that natural variation?

Re: Grammarly is offering ‘expert’ AI reviews from famous dead and living writers

#83

Post by Talanes »

simianwords wrote: post #58
mysterydip wrote: post #57

Earlier quoted context omitted.

Is the reason it can show steps for solving an integral because the training set contained webpages or books showing how to do it?

if we have steps for understanding any author's english and creative process (generally not specific to an author) would you agree then it is possible for an llm to do it?

The real sticking point for me is I don't even believe that authors themselves FULLY understand their process. The idea that anybody could achieve such full introspection as to understand and articulate every little thing that influences their output seems astoundingly improbable.

Re: Grammarly is offering ‘expert’ AI reviews from famous dead and living writers

#84

Post by netdevphoenix »

RobRivera wrote: post #78
simianwords wrote: post #21

Earlier quoted context omitted.

i don't get what the point of what you are saying is? i can ask it to explain how to solve an integral right now with steps. i can ask it to tell me how to write like a person X right now.

Actually this is the crux and the nuance which makes discussing LLM specifics a pain in the general space. If you built an LLM exclusively on the writings and letters of John Steinbeck, you could NOT tell the LLM to solve an integral for you amd expect it to be right. Instead what you will receive is a text that follows a statistically derived most likely (in accordance to the perplexity tuning) response to such a qu…

> If you built an LLM exclusively on the writings and letters of John Steinbeck, you could NOT tell the LLM to solve an integral for you amd expect it to be right.

Isn't this obvious? There is not enough latent knowledge of math there to enable current LLMs to approximate anything resembling an integral.

Re: Grammarly is offering ‘expert’ AI reviews from famous dead and living writers

#85

Post by re-thc »

empath75 wrote: post #79
plewd wrote: post #37

Earlier quoted context omitted.

like OP originally said, the LLM doesn't have access to the actual process of the author, only the completed/refined output. Not sure why you need a concrete example to "test", but just think about the fact that the LLM has no idea how a writer brainstorms, re-iterates on their work, or even comes up with the ideas in the first place.

> has no idea how a writer brainstorms This isn't true in general, and not even true in many specific cases, because a great deal of writers have described the process of writing in detail and all of that is in their training data. Claude and chatgpt very much know how novels are written, and you can go into claude code and tell it you want to write a novel and it'll walk you through quite a lot of it -- worldbuildin…

> because a great deal of writers have described the process of writing in detail

And that's often inaccurate - just as much as asking startup founders how they came to be.

Part of it is forgot, part of it is don't know how to describe it and part of it is don't want to tell you so.

Re: Grammarly is offering ‘expert’ AI reviews from famous dead and living writers

#86

Post by netdevphoenix »

mysterydip wrote: post #62
simianwords wrote: post #58

Earlier quoted context omitted.

if we have steps for understanding any author's english and creative process (generally not specific to an author) would you agree then it is possible for an llm to do it?

Repeating a process, yes for sure, even (pseudorandom?) variations on a process. Understanding a process is a different question, and I’m not sure how you would measure that. In school we would have a test with various questions to show you understand the concept of addition, for example. But while my calculator can perfectly add any numbers up to its memory limit, it has no understanding of addition.

> while my calculator can perfectly add any numbers up to its memory limit, it has no understanding of addition.

"my calculator can perfectly add any numbers up to its memory limit" This kind of anthropomorphic language is misleading in these conversations. Your calculator isn't an agent so it should not be expected to be capable of any cognition.

Re: Grammarly is offering ‘expert’ AI reviews from famous dead and living writers

#87

Post by RobRivera »

netdevphoenix wrote: post #84
RobRivera wrote: post #78

Earlier quoted context omitted.

Actually this is the crux and the nuance which makes discussing LLM specifics a pain in the general space. If you built an LLM exclusively on the writings and letters of John Steinbeck, you could NOT tell the LLM to solve an integral for you amd expect it to be right. Instead what you will receive is a text that follows a statistically derived most likely (in accordance to the perplexity tuning) response to such a qu…

> If you built an LLM exclusively on the writings and letters of John Steinbeck, you could NOT tell the LLM to solve an integral for you amd expect it to be right. Isn't this obvious? There is not enough latent knowledge of math there to enable current LLMs to approximate anything resembling an integral.

Its obvious to me.

Its obvious to you.

It isnt obvious to the person I am responding to, and it isnt obvious to majority of individuals I speak with on the matter (which is why AI, personally, is in the bucket of religion amd politics for polite conversation to simply avoid)

Re: Grammarly is offering ‘expert’ AI reviews from famous dead and living writers

#88

Post by Talanes »

netdevphoenix wrote: post #84
RobRivera wrote: post #78

Earlier quoted context omitted.

Actually this is the crux and the nuance which makes discussing LLM specifics a pain in the general space. If you built an LLM exclusively on the writings and letters of John Steinbeck, you could NOT tell the LLM to solve an integral for you amd expect it to be right. Instead what you will receive is a text that follows a statistically derived most likely (in accordance to the perplexity tuning) response to such a qu…

> If you built an LLM exclusively on the writings and letters of John Steinbeck, you could NOT tell the LLM to solve an integral for you amd expect it to be right. Isn't this obvious? There is not enough latent knowledge of math there to enable current LLMs to approximate anything resembling an integral.

Now what if we ask the LLM to write about social media? Do you think the output would be similar to what you'd get if we had a time machine to bring the actual man back and have him form his own thoughts firsthand?

Re: Grammarly is offering ‘expert’ AI reviews from famous dead and living writers

#89

Post by AlotOfReading »

empath75 wrote: post #79
plewd wrote: post #37

Earlier quoted context omitted.

like OP originally said, the LLM doesn't have access to the actual process of the author, only the completed/refined output. Not sure why you need a concrete example to "test", but just think about the fact that the LLM has no idea how a writer brainstorms, re-iterates on their work, or even comes up with the ideas in the first place.

> has no idea how a writer brainstorms This isn't true in general, and not even true in many specific cases, because a great deal of writers have described the process of writing in detail and all of that is in their training data. Claude and chatgpt very much know how novels are written, and you can go into claude code and tell it you want to write a novel and it'll walk you through quite a lot of it -- worldbuildin…

The distinction being made is the difference between intellectual knowledge and experience, not originality.

Imagine a interviewing a particularly diligent new grad. They've memorized every textbook and best practices book they can find. Will that alone make them a senior+ developer, or do they need a few years learning all the ways reality is more complicated than the curriculum?

LLMs aren't even to that level yet.

Re: Grammarly is offering ‘expert’ AI reviews from famous dead and living writers

#90

Post by mikeocool »

chilipepperhott wrote: post #80

I know all press is good press... but there are limits. If it feels like Grammarly does not respect your right to digital sovereignty, it is because it does not.

It almost seems like this whole feature is designed to invite law suits.

Seems pretty likely usage of Grammarly's core product has cratered in the past few years. Not totally hard to imagine one of the big AI labs paying their legal fees in exchange for putting this out there and kick starting the legal process on some of these issues.

Post reply on HN