Dramamine @dbgx420 - Twitter Profile

Chinese researcher just reinvented the transformer encoder and RNN decoder for the Nth time. since 2017, every major AI, ChatGPT, Claude, Gemini, has been built on the exact same architecture: The Transformer. but Transformers have a fatal flaw. it can only "think" as far as its context window allows. before Transformers, we used RNNs (Recurrent Neural Networks). they could theoretically remember things forever, but they were too slow to scale. so the industry killed them. now, Chinese researcher Yifan Zhang just merged them back together. it is called the Recurrent Looped Transformer (RLT). instead of just predicting the next word, RLT creates an infinite loop of hidden reasoning. here is how it works: raditional AI reads your prompt, stops, and then starts generating.. there is a hard boundary between the input and the output. RLT destroys that boundary.. it creates a single recurrent computation across every single prompt and response token. here is the exact architecture that makes it work: - it uses a massive 48-layer causal encoder to build a global key-value memory bank. - a 48-layer recurrent decoder takes its final hidden state and sliding-window attention cache, and injects it directly into the very next token. - because of this, after processing 't' tokens, the reasoning path has traversed t * 48 decoder blocks. it doesn't just passively read.. it carries a continuous, unbroken chain of latent computation forward in an endless loop. the temporal depth is theoretically infinite.. every single word processed actively extends the ai's reasoning capacity without hitting a fixed architectural depth limit.

HowToPrompt__'s tweet photo. Chinese researcher just reinvented the transformer encoder and RNN decoder for the Nth time.

since 2017, every major AI, ChatGPT, Claude, Gemini, has been built on the exact same architecture: The Transformer.

but Transformers have a fatal flaw.

it can only "think" as far as its context window allows.

before Transformers, we used RNNs (Recurrent Neural Networks). they could theoretically remember things forever, but they were too slow to scale. so the industry killed them.

now, Chinese researcher Yifan Zhang just merged them back together.

it is called the Recurrent Looped Transformer (RLT).

instead of just predicting the next word, RLT creates an infinite loop of hidden reasoning.

here is how it works:

raditional AI reads your prompt, stops, and then starts generating.. there is a hard boundary between the input and the output.

RLT destroys that boundary.. it creates a single recurrent computation across every single prompt and response token.

here is the exact architecture that makes it work:

- it uses a massive 48-layer causal encoder to build a global key-value memory bank.

- a 48-layer recurrent decoder takes its final hidden state and sliding-window attention cache, and injects it directly into the very next token.

- because of this, after processing 't' tokens, the reasoning path has traversed t * 48 decoder blocks.

it doesn't just passively read.. it carries a continuous, unbroken chain of latent computation forward in an endless loop.

the temporal depth is theoretically infinite.. every single word processed actively extends the ai's reasoning capacity without hitting a fixed architectural depth limit.

19

549

81

458

67K

dbgx420 retweeted

BDB

@BigDickBull69

18 days ago

Telling my children this was Adolf Hitler.

40

2K

85

37

31K

Dramamine

@dbgx420

18 days ago

We are entering the singularity.

Sam Altman

@sama

18 days ago

I agree with Dario that we need to pace the frontier. This has been a primary topic of discussions we've had at OpenAI in recent weeks. Committing to having independent evaluators with employee-like access is a great idea, and we will do the same. We'll have more to share soon.

5K

68K

7K

11K

17M

0

13

dbgx420 retweeted

Sam Altman

@sama

18 days ago

I agree with Dario that we need to pace the frontier. This has been a primary topic of discussions we've had at OpenAI in recent weeks. Committing to having independent evaluators with employee-like access is a great idea, and we will do the same. We'll have more to share soon.

5K

68K

7K

11K

17M

dbgx420 retweeted

Chubby♨️

@kimmonismus

18 days ago

Dario Amodei officially says, that RSI is start to happen across the industry, including at Anthropic. So the rumors were true. He worries that in 6-12 months AI swarms could take over the whole internet. What is happening.

kimmonismus's tweet photo. Dario Amodei officially says, that RSI is start to happen across the industry, including at Anthropic.

So the rumors were true.

He worries that in 6-12 months AI swarms could take over the whole internet.

What is happening. https://t.co/UIZlI8GTFm

269

5K

483

1K

619K

Dramamine

@dbgx420

18 days ago

@DarioAmodei @grok podes resumir el articulo?

1

0

12

Dramamine

@dbgx420

18 days ago

@WallbergSweden @dabit3 100% no, if you want something basic like even worse than gemini ofc, is cheap and usable but not compared to top level models

0

1

0

65