neural_morty @neural_morty

trying to impress rick Joined June 2025

Tweets

12
Followers

7
Following

42
Likes

10

Shiva @shivaaaaa23

2 months ago

the whole idea of nvidia dlss can be applied to webrtc, essentially using VFI to fill in the gaps of jitters you experince due to packet loss, but the model will a lot of computation and it has to be quick as fuck, the gap between detecting the last ack bit and generating ....

2 1 2 95 0

Shiva @shivaaaaa23

2 months ago

youtube.com/watch?v=OE0_-g… this mofo was the inspiration

0 1 0 80 0

neural_morty @neural_morty

2 months ago

What tf is he onto.

dane @danesonance

2 months ago

What tf is he onto.

840 823 10K 15.7M 1K

0 0 0 26 0

ARC Prize @arcprize

2 months ago

Grok 4 (Thinking) achieves new SOTA on ARC-AGI-2 with 15.9% This nearly doubles the previous commercial SOTA and tops the current Kaggle competition SOTA

245 743 5K 7.3M 728

Download Image

neural_morty @neural_morty

2 months ago

It's just stitching shit up and then optimizing, then realise a week later that it could've been done so much better.

0 0 1 28 0

neural_morty @neural_morty

2 months ago

Yet again working with hybrid models.

0 0 1 32 0

neural_morty @neural_morty

2 months ago

Till now i have been asked to clone designmumbai.com i will be using react, the website was made on some CMS and i have been asked to completely shift that to Node. Will be using Redis and Kafka for caching and low latency operations and distribution respectively.

0 0 6 52 0

Download Image

neural_morty @neural_morty

2 months ago

i am high, i see gradients on the perfectly round butts

0 0 1 25 0

Sanskar Pandey @sanskxr02

2 months ago

ablations underscore the core idea: it's not about GRUs. in appendix D, we swap the GRU for a TCN - same [CLS]/sequence split, same top-1 gate. performance holds. routing adapts. hecto is a modular scaffold. the expert is a choice. a complete plug and play module.

1 1 15 318 0

Sanskar Pandey @sanskxr02

2 months ago

hecto was trained in a controlled setting - 5 epochs with batch size 16. even then, it holds steady on AG News, SST-2, and HotpotQA, trailing homogeneous MoEs by <1%. at batch size 64, performance improves significantly - validating the design under scale.

1 1 13 366 0

Download Image

Sanskar Pandey @sanskxr02

2 months ago

we set out to rethink how models allocate reasoning. today we’re releasing hecto,a modular mixture-of-experts model combining GRU and FFNN to specialize computation per input. no supervision. no backing. just a team of undergrads building what didn’t exist.