Nitish

building tɘxt - AI text classifier | farming biodynamic 🍓 + 🌶️ + 🍅

[Nitish @Nitieo]

just got called 'The human' by an LLM model. fml, this is about to turn ugly

[Nitish @Nitieo]

@dhh I have like a million unorganised scripts at this point. I'm pretty sure half of them are dupes.

[Nitish @Nitieo]

@antoniosarosi have you seen the abrv used in c? 😂 (abbreviations)

[Nitish @Nitieo]

context changes everything, literally.

[Yann LeCun @ylecun]

Dude, your stupid and utterly ignorant attacks don't deserve that anyone spend any time responding to them.
How much do enjoy doing character assassination while cowardly hiding your identity behind a random handle?
Own your opinions.
You have absolutely no idea of what you are talking about here.

Shared weights were in the original backprop paper in the PDP book (look up to T-C problem).
TDNN (or 1D CNN) were actually invented and published by Geoff Hinton and Kevin Lang at CMU.
They published a tech report (not a journal paper) because they weren't beating the best CMU ASR system with it.
Then, Alex Waibel (who knew nothing about neural nets at the time) ***TOOK THE CODE*** from Kevin, went to ATR in Japan, got some better results than the ATR system (which wasn't as good as the CMU system) and wrote a journal paper.
Geoff and Kevin were pissed as hell (I was a postdoc with Geoff when this whole thing happened).
My ConvNet papers cite Kevin's tech report, not Alex's. Alex was actually mad at me for this.

The original TDNNs from Kevin had only one convolutional layer.
The first *real* (multilayer) TDNNs with pooling/subsampling for speech recognition were done by Léon Bottou. He could recognize whole words with it (the original TDNN could only do phonemes). Yoshua Bengio also had results on this a bit later.
I hired both of them at Bell Labs because they also worked on sentence-level training with backprop through a time alignment. We used similar ideas for our check reader.

[Nitish @Nitieo]

teleport between SF and LA is a much more realistic idea today.

[jess lozano schmitt @JessLozanoS]

start up idea: functional train system
between SF and LA

[Nitish @Nitieo]

@JaySahnan not if you're clicking pictures and uploading them on twitter.

[Nitish @Nitieo]

@ai_for_success not just ads. it's going to become a full fledged marketplace very soon

[Nitish @Nitieo]

@toddsaunders well ARR is off the table since Stripe introduced validation

[Nitish @Nitieo]

@JustJake so why not a k8s style sandbox environment?

[Nitish @Nitieo]

@TheAhmadOsman his name is "captain_creatine" , what did you think he would say? 😆

[Nitish @Nitieo]

@elithrar @Cloudflare @karanjagtiani04 seems zero-copy, should be comparable.

[Nitish @Nitieo]

@lauriewired I think a dev was probably stuck alone pushing system updates on thanksgiving, and got offended with your last post .. decided to have some fun with your acc

[Nitish @Nitieo]

@Ethan_is_online parties anywhere really.

[Nitish @Nitieo]

@LundukeJournal I wrote this tweet using Servo, which is written in Rust. 🤭

[Nitish @Nitieo]

@ohmypy get out is not exactly proper either.

[Nitish @Nitieo]

@ryanseanbadger @DataFast_ and the best part is it's probably not even vibe coded.

[Nitish @Nitieo]

@andy_pavlo this guy needs intellectual seppuku - your research and open access teaching is probably the single best thing to ever happen to databases.

[Nitish @Nitieo]

@__tinygrad__ and why do you need a mac for this?

[Nitish @Nitieo]

@whoiskatrin unlimited flat whites @ shreeji part of the offer?

[Nitish @Nitieo]

women don't apply to yc?

[Tom Blomfield @t_blom]

Getting the YC batch together to share fundraising horror stories from the last few days.

The behavior of some investors is shocking 🤦‍♂️

Founders all talk. Stop it.