Will we have any progress on the interpretability of State Space Model LLM’s in 2024?
Plus
12
Ṁ312Jan 1
71%
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.
This question is managed and resolved by Manifold.
Get
1,000
and3.00
Related questions
Related 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?
40% chance
Will an LLM Built on a State Space Model Architecture Have Been SOTA at any Point before EOY 2027? [READ DESCRIPTION]
43% chance
Will there be an open source LLM as good as GPT4 by the end of 2024?
68% chance
Will there be a gpt-4 quality LLM with distributed inference by the end of 2024?
27% chance
Will mechanistic interpretability be essentially solved for GPT-2 before 2030?
29% chance
Will a lab train a >=1e26 FLOP state space model before the end of 2025?
24% chance
By 2028 will we be able to identify distinct submodules/algorithms within LLMs?
75% chance
Will OpenAI release an LLM moderation tool in 2024?
64% chance
[Situational awareness] Will pre-2026 LLMs achieve token-output control?
30% chance
will top LLM models use formal methods by EOY 2024?
24% chance