Will we have any progress on the interpretability of State Space Model LLM’s in 2024? | Manifold

Will we have any progress on the interpretability of State Space Model LLM’s in 2024?

#AI #LLMs #Mechanistic interpretability

11

65

Ṁ112

Ṁ430

2025

65%

chance

1D

1W

1M

ALL

State Space Models like Mamba introduce new possibilities, as States are a new object type, a compressed snapshot of a mind at a point in time which can be saved, restored, and interpreted. But a cursory search didn’t turn up any work on interpreting either States or State Space Models.

This resolves Yes if research comes out that makes any significant interpretability progress into a state space large language model. I will not bet on this market.

Get Ṁ200 play money

Sort by:

Putting a 1k limit order for "YES" at 50% if anyone wants to take it.

I'm watching this but the notion of "any significant ... progress" is too vague for me to trade.

Related in AI

OpenAI Monday Livestream Prop Bets [10 AM PT]

What will be announced by OpenAI during Monday's livestream? [ADD RESPONSES]

See more AI questions

Related in LLMs

Will OpenAI release GPT 4.5 or GPT 5 before June 2024?

+58% 1d68% chance

Will there be a major controversy about if an OpenAI LLM counts for a Manifold market because of its exact name in 2024?

See more LLMs questions

Related in Mechanistic interpretability

By the end of 2026, will we have transparency into any useful internal pattern within a Large Language Model whose semantics would have been unfamiliar to AI and cognitive science in 2006?

Is attention all you need? (transformers SOTA in 2027)

See more Mechanistic interpretability questions

More related questions

Will AI be able to solve confusing but elementary geometric reasoning problems in 2024?

Will a model costing >$30M be intentionally trained to be more mechanistically interpretable by end of 2027? (see desc)

By 2028 will we be able to identify distinct submodules/algorithms within LLMs?

Will language models be able to solve simple graphical mazes by the end of 2025?

Will we be able to estimate the feature importance curve or feature sparsity curve of real models? (2024 end)

Will mechanistic interpretability be essentially solved for GPT-2 before 2030?

Will there be a gpt-4 quality LLM with distributed inference by the end of 2024?

Will an LLM Built on a State Space Model Architecture Have Been SOTA at any Point before EOY 2027? [READ DESCRIPTION]

Will there be an LLM which can do fluent conlang translations by EOY 2024?

AI questions

OpenAI Monday Livestream Prop Bets [10 AM PT]

What will be announced by OpenAI during Monday's livestream? [ADD RESPONSES]

LLMs questions

Will OpenAI release GPT 4.5 or GPT 5 before June 2024?

Will there be a major controversy about if an OpenAI LLM counts for a Manifold market because of its exact name in 2024?

Mechanistic interpretability questions

By the end of 2026, will we have transparency into any useful internal pattern within a Large Language Model whose semantics would have been unfamiliar to AI and cognitive science in 2006?

Is attention all you need? (transformers SOTA in 2027)

Related questions

Will AI be able to solve confusing but elementary geometric reasoning problems in 2024?

Will mechanistic interpretability be essentially solved for GPT-2 before 2030?

Will a model costing >$30M be intentionally trained to be more mechanistically interpretable by end of 2027? (see desc)

Will there be a gpt-4 quality LLM with distributed inference by the end of 2024?

By 2028 will we be able to identify distinct submodules/algorithms within LLMs?

Will an LLM Built on a State Space Model Architecture Have Been SOTA at any Point before EOY 2027? [READ DESCRIPTION]

Will language models be able to solve simple graphical mazes by the end of 2025?

Will there be an LLM which can do fluent conlang translations by EOY 2024?

Will we be able to estimate the feature importance curve or feature sparsity curve of real models? (2024 end)