On January 1, 2027, a Transformer-like model will continue to hold the state-of-the-art position in most benchmark | Manifold

On January 1, 2027, a Transformer-like model will continue to hold the state-of-the-art position in most benchmark

38

1kṀ4190

2026

80%

chance

1D

1W

1M

ALL

Tracking external bet: https://www.isattentionallyouneed.com/

Get

1,000

to start trading!

Sort by:

What constitutes Transformer-like?

Is it all, or some, of these?

Token inputs, token outputs
Positional encoding
(MH QKV SDPA -> MLP) layers
Residual connections

bought Ṁ50 NO

https://arxiv.org/abs/2501.00663

Titans: Learning to Memorize at Test Time

Abstract page for arXiv paper 2501.00663: Titans: Learning to Memorize at Test Time

@JaundicedBaboon Let's see if it can leave the academia limbo where the Mamba's got stuck...

https://x.com/_philschmid/status/1846452029582959012

@MalachiteEagle Transformers, yes. Attention, not really:

followed by two shared attention blocks.

https://blog.rwkv.com/p/eagle-7b-soaring-past-transformers

It even links the wager page in its bragging points:

All while being an “Attention-Free Transformer”

I thought this wager was made today haha

Does this strictly resolve to the outcome of the bet?

@FranekZak Yep. Whatever details they come up with are in.

Related questions

A major ML paper demonstrates symbolic-enhanced transformer successor outperforming standard transformers by March 2025

Will the most capable, public multimodal model at the end of 2027 in my judgement use a transformer-like architecture?

Will any model get above human level on the Simple Bench benchmark before September 1st, 2025.

By EOY 2025, will the model with the lowest perplexity on Common Crawl will not be based on transformers?

When will a non-Transformer model become the top open source LLM?

Will transformers still be the dominant DL architecture in 2026?

Will Transformer based architectures still be SOTA for language modelling by 2026?

On LMSys, what will be the difference between the top model and GPT-4-1106 on Jan 1 2026?

Will superposition in transformers be mostly solved by 2026?

By the start of 2026, will I still think that transformers are the main architecture for tasks related to natural language processing?

Related questions

A major ML paper demonstrates symbolic-enhanced transformer successor outperforming standard transformers by March 2025

Will transformers still be the dominant DL architecture in 2026?

Will the most capable, public multimodal model at the end of 2027 in my judgement use a transformer-like architecture?

Will Transformer based architectures still be SOTA for language modelling by 2026?

Will any model get above human level on the Simple Bench benchmark before September 1st, 2025.

On LMSys, what will be the difference between the top model and GPT-4-1106 on Jan 1 2026?

By EOY 2025, will the model with the lowest perplexity on Common Crawl will not be based on transformers?

Will superposition in transformers be mostly solved by 2026?

When will a non-Transformer model become the top open source LLM?

By the start of 2026, will I still think that transformers are the main architecture for tasks related to natural language processing?

© Manifold Markets, Inc.•Terms + Mana-only Terms•Privacy•Rules