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

BrainGPT turns thoughts into text

iflscience.com

Post reply on HN
Print view View original

111–120 of 208 posts

Re: BrainGPT turns thoughts into text

#111

Post by RaftPeople »

spookybones wrote: post #18
admax88qqq wrote: post #6

Earlier quoted context omitted.

Combine hallucinations with police adopting this as the new polygraph and this could take a pretty bad turn. Cool tech though, lots of positive applications too.

I wonder if a subject has to train it first, such as by reading a bunch of prompts while trying to imagine them. Or, are our linguistic neural networks all very similar? If the former is true, it would at least be a bit harder to work as a polygraph. You wouldn't be able to just strap on the helmet and read someone's thoughts accurately.

Yes it requires training for each individual. In addition, they tested using a trained model from one person to try to decode a different person and the results were no better than chance.

They also said that the person must cooperate for the decoding to work, meaning the person could reduce the decoding accuracy by thinking of specific things (e.g. counting).

CORRECTION: The paper I read was not the correct paper, ignore this comment. The actual paper states that the model is transferrable across subjects.

Re: BrainGPT turns thoughts into text

#112

Post by darkclouds »

joenot443 wrote: post #7

Ground Truth: Bob attended the University of Texas at Austin where he graduated, Phi Beta Kappa with a Bachelor’s degree in Latin American Studies in 1973, taking only two and a half years to complete his work, and obtaining generally excel- lent grades. Predict: was the University of California at Austin in where he studied in Beta Kappa in a degree of degree in history American Studies in 1975. and a one classes a…

[dead]

Re: BrainGPT turns thoughts into text

#114

Post by callalex »

opdahl wrote: post #32

It’s crazy to me that someone has developed a technology that literally reads peoples mind fairly accurately and its just like a semi popular post on Hacker News.

Well, the results marketed by this study are vastly overstated, bordering on unethical lying. Figure 1 is literally just made up. See discussion here: https://news.ycombinator.com/item?id=38674971

Re: BrainGPT turns thoughts into text

#115

Post by fortran77 »

blindriver wrote: post #72
MoSattler wrote: post #35

Earlier quoted context omitted.

First use will be for criminal suspects, to "save lives". Then its use slowly expands from there.

"For the children" is the first excuse usually.

Exactly! Strap it on anyone who has to work with children to see if they ever have any untoward thoughts.... Then move on to everyone else.

Re: BrainGPT turns thoughts into text

#117

Post by mike_hearn »

explaininjs wrote: post #108
PaulScotti wrote: post #88

Earlier quoted context omitted.

Guys Figure 1 is not real results, it's an illustration of the "goal" of the paper. The real results are in Table 3. And are much worse.

Interesting ploy. Present far-better-than-achieved results right on the front page with no text to explain their origin^, but make them poor enough quality to make it seem as if they might be real. ^ "Overall illustration of translate EEG waves into text through quantised encoding." doesn't count.

Urgh. And it gets worse from there. The bugs list on the repo has a closed and locked bug report from someone claiming that their code is using teacher forcing!

https://github.com/duanyiqun/DeWave/issues/1

In a normal recurrent neural network, the model predicts token-at-a-time. It predicts a token, and that token is appended to the total prediction so far which is then fed back into the model to generate the next token. In other words, the network generates all the predictions itself based off its own previous outputs and the other inputs (brainwaves in this case), meaning that a bad prediction can send the entire thing off track.

In teacher forcing that isn't the case. All the tokens up to the point where it's predicting are taken from the correct inputs. That means the model is never exposed to its own previous errors. But of course in a real system you don't have access to the correct inputs, so this is not feasible to do in reality.

The other repo says:

"We have written a corrected version to use model.generate to evaluate the model, the result is not so good"

but they don't give examples.

This problem completely invalidates the paper's results. It is awful that they have effectively hidden and locked the thread in which the issue was reported. It's also kind of nonsensical that people doing such advanced ML work are claiming they accidentally didn't know the difference between model.forward() and model.generate(). I mean I'm not an ML researcher and might have mangled the description of teacher forcing, but even I know these aren't the same thing at all.

Re: BrainGPT turns thoughts into text

#118

Post by Jensson »

Can we train an LLM based on brainwaves rather than written text? Seems to be closer to how we actually think and thus should enable the LLM to learn to think rather than just learn to mimic the output.

For example, when writing we have often gone done many thought paths, evaluated each and backtracked etc, but none of that is left in the text an LLM trains on today. Recording brainwaves and training on that is probably the best training data we could get for LLMs.

Getting that data wouldn't be much harder than paying humans to solve problems with these hats on recording their brainwaves.

Re: BrainGPT turns thoughts into text

#119

Post by Jensson »

valine wrote: post #89
jprete wrote: post #66

Earlier quoted context omitted.

I would agree if I didn't think there were really strong incentives and precedents for abuse of the technology.

We have laws that prevent people being subjected to brain surgery against their will. The credit score concept is ridiculous. The real battle will be with law enforcement who get a warrant to look at your brain in an MRI.

You don't need brain surgery or an MRI to scan a brain, this just uses an EEG.

Re: BrainGPT turns thoughts into text

#120

Post by oldesthacker »

PaulScotti wrote: post #88
joenot443 wrote: post #7

Ground Truth: Bob attended the University of Texas at Austin where he graduated, Phi Beta Kappa with a Bachelor’s degree in Latin American Studies in 1973, taking only two and a half years to complete his work, and obtaining generally excel- lent grades. Predict: was the University of California at Austin in where he studied in Beta Kappa in a degree of degree in history American Studies in 1975. and a one classes a…

Guys Figure 1 is not real results, it's an illustration of the "goal" of the paper. The real results are in Table 3. And are much worse.

The results of Table 3 are not really exciting. Could this change with 100 times more data? The key novelty in the specific context of this particular application is the quantized variational encoder used "to derive discrete codex encoding and align it with pre-trained language models."
Post reply on HN