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

181–190 of 214 posts

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

#181

Post by simianwords »

simianwords wrote: post #161
bigfishrunning wrote: post #160

Earlier quoted context omitted.

If you look at the "workflow" section of that page, they had to add a bunch of scaffolding around telling the model what moves are legal -- an llm can't keep enough context to know how to play chess; only to choose an advantageous move from a given list. But feel free to "cherry pick".

why do you think this falsifies that it can't reason?

i ran the benchmark without the valid moves tool as well as the three mistakes grace and gpt-5.4 holds well. it can achieve 1000 ELO which is much higher than my own.

this clearly tells me that GPT is good at chess, at least better than a normal person who has played ~30-40 games in their life.

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

#182

Post by latexr »

thesuitonym wrote: post #179
latexr wrote: post #55

Earlier quoted context omitted.

You’re not counting all the office workers who have to write reports or emails, or all the scammers who write those websites to manipulate SEO or show you ads.

If you fall into the camp of office workings needing to write reports or emails, maybe think twice about putting your name on AI garbage.

Everyone should think twice about putting their name on AI garbage, or garbage of any kind. But wishing doesn’t stop it from happening, especially when companies are explicitly selling you on doing just that. Remember the Apple Intelligence office ads?

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

#183

Post by simianwords »

tovej wrote: post #165
simianwords wrote: post #134

Earlier quoted context omitted.

>You need to show me an LLM applying writing techniques do not have examples in its corpus. why are you bringing this constraint?

Because the entire point is the LLM cannot understand text about text. If someone has already done the work of giving an example of how to produce text according to a process, we have no way of knowing if the LLM has followed the process or copied the existing example. And my point of course is that copying examples is the only way that LLMs can produce text. If you use an author who has been so analyzed to death tha…

>Because the entire point is the LLM cannot understand text about text.

you have asked for an LLM to read a single interview and produce text that sounds similar to the author based on the techniques on that single interview.

https://claude.ai/share/cec7b1e5-0213-4548-887f-c31653a6ad67 here is the attempt. i don't think i could have done much better.

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

#184

Post by DonHopkins »

ErroneousBosh wrote: post #97
DonHopkins wrote: post #22

Earlier quoted context omitted.

You're not thinking, just regurgitating catch phrases that are factually incorrect hallucinations. So how are you any better than an LLM?

Which part is "factually incorrect"?

Several parts of your claim are incorrect.

First, modern LLMs are not "a huge table of phrases". They are neural networks with billions of learned parameters that generate tokens by computing probability distributions over vocabulary given prior context. There is no lookup table of stored sentences.

Second, Eliza-style bots used explicit scripted pattern matching rules. LLMs instead learn statistical representations from large corpora and can generalize to produce novel sequences that were never present in the training data.

Kent Pitman's Lisp Eliza from MIT-AI's ITS History Project (sites.google.com):

https://news.ycombinator.com/item?id=39373567

https://sites.google.com/view/elizagen-org/

https://sites.google.com/view/elizagen-org/original-eliza

Third, while "pattern matching" is sometimes used informally, it’s misleading technically. Transformers perform high-dimensional vector computations and attention over context to model relationships between tokens. That’s very different from rule-based pattern matching.

You can certainly debate whether LLMs "think", but describing them as "Eliza with a big phrase table" is not an accurate description of how they work.

You have the resources available at your fingertips to learn what the truth is, how LLMs actually work. You could start with Wikipedia, or read Steven Wolfram's article, or simply ask an LLM to explain how it works to you. It's quite good at that, while an Eliza bot certainly can't explain to you how it works, or even write code.

What Is ChatGPT Doing … and Why Does It Work?

https://writings.stephenwolfram.com/2023/02/what-is-chatgpt-...

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

#185

Post by bigstrat2003 »

jacquesm wrote: post #126
PessimalDecimal wrote: post #122

Earlier quoted context omitted.

You probably mean necromancy.

> You probably mean necromancy. I probably did not. Then I would have written that. They are fucking over the dead. They are clearly not communicating with the dead.

"fucking over" as an expression has nothing to do with sex, so it wouldn't qualify as necrophilia.

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

#186

Post by jacquesm »

bigstrat2003 wrote: post #185
jacquesm wrote: post #126

Earlier quoted context omitted.

> You probably mean necromancy. I probably did not. Then I would have written that. They are fucking over the dead. They are clearly not communicating with the dead.

"fucking over" as an expression has nothing to do with sex, so it wouldn't qualify as necrophilia.

Neither does digital. Is it pedant day today or did I miss the memo?

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

#187

Post by bigstrat2003 »

simianwords wrote: post #153
bigfishrunning wrote: post #143

Earlier quoted context omitted.

> And LLMs do have understanding. They absolutely do not. If you "ask it how it came up with the process in natural language" with some input, it will produce an output that follows, because of the statistics encoded in the model. That output may or may not be helpful, but it is likely to be stylistically plausible. An LLM does not think or understand; it is merely a statistical model (that's what the M stands for!)

how would you empirically disprove that it doesn't have understanding? i can prove that it does have understanding because it behaves exactly like a human with understanding does. if i ask it to solve an integral and ask it questions about it - it replies exactly as if it has understood. give me a specific example so that we can stress test this argument. for example: what if we come up with a new board game with a c…

> how would you empirically disprove that it doesn't have understanding?

The complete failure of Claude to play Pokemon, something a small child can do with zero prior instruction. The "how many r's are in strawberry" question. The "should I drive or walk to the car wash" question. The fact that right now, today all models are very frequently turning out code that uses APIs that don't exist, syntax that doesn't exist, or basic logic failures.

The cold hard reality is that LLMs have been constantly showing us they don't understand a thing since... forever. Anyone who thinks they do have understanding hasn't been paying attention.

> i can prove that it does have understanding because it behaves exactly like a human with understanding does.

First, no it doesn't. See my previous examples that wouldn't have posed a challenge for any human with a pulse (or a pulse and basic programming knowledge, in the case of the programming examples). But even if it were true, it would prove nothing. There's a reason that in math class, teachers make kids show their work. It's actually fairly common to generate a correct result by incorrect means.

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

#188

Post by weird-eye-issue »

dwb wrote: post #76
weird-eye-issue wrote: post #40

Earlier quoted context omitted.

Yeah but obviously my point in this context is that it doesn't. Its not like I said to replace the word with "potato". Thanks for your genius comment.

It changes the meaning significantly. An LLM has very little in common with a human student.

How so? I see lots of similarities both in the training and inference/prompting stages.

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

#189

Post by bigstrat2003 »

NuclearPM wrote: post #164
latexr wrote: post #66

Earlier quoted context omitted.

I’m pretty sure you can think of one yourself, I’m not going to play this game. Now it’s 5.4 Thinking, before that it was 5.3, before that 5.2, 5.1, 5, before that it was 4… At every stage there’s someone saying “oh, the previous model doesn’t matter, the current one is where it’s at”. And when it’s shown the current model can’t do something, there’s always some other excuse. It’s a profoundly bad faith argument, the…

Caught and gamed? What do you mean?

He means that if the problem becomes known, the AI companies will hack in a workaround rather than solving the problem by making the model more intelligent. Given that they have been caught cheating in that way in the past, I can't blame the GP for not sharing his tests.

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

#190

Post by mynameisvlad »

jacquesm wrote: post #177
mynameisvlad wrote: post #174

Earlier quoted context omitted.

> You probably mean necromancy. You: > I probably did not. Then I would have written that. They are fucking over the dead. They are clearly not communicating with the dead. A less snarky and hostile version: > I actually didn't! I specifically meant that they are fucking over the dead. Pretty much the same content, and it makes you sound like you actually want to interact with other people. Even in your paragraph lon…

Thank you. I'm 60+ and I think I'm past saving, but I appreciate your effort to tone police HN. As well as your own exemplary behavior: https://news.ycombinator.com/item?id=46653114 https://news.ycombinator.com/item?id=45505708 https://news.ycombinator.com/item?id=45334298 And probably others besides.

[flagged]
Post reply on HN