LLM agent is able to reliably beat Slay the Spire 2 before EOY 2027

MANIFOLD

Ṁ10kṀ2.6k

2027

39%

chance

ALL

Ascension 0

Needs to wins 3 consecutive runs

Savescumming does not count

The LLM agent is allowed to take notes on its failed attempts and craft hooks that generate a higher informational representation of its current state.

The LLM is not allowed to use or develop a solver, though it is permitted to do post analysis and craft heuristics

Market context

Technology

Technical AI Timelines

Gaming

LLMs

Get

1,000

to start trading!

People are also trading

Will an LLM beat a Super GM Bot on chess.com by 2028?

23% chance

Will an LLM from OpenAI beat me in chess by the end of 2026?

52% chance

Will a publicly available LLM/Agent beat a 2000 rated Elo chess player online rapid chess by March 2027?

67% chance

Will an LLM beat me in a game of chess by the end of 2027?

62% chance

Will LLMs Daydream by EOY 2026?

25% chance

Will an LLM from OpenAI beat me in chess by the end of 2028?

71% chance

By 2028 will an assisted LLM beat the Ender Dragon?

81% chance

Will any LLM produce a reasonable poker simulation, as judged by Nate Silver, by the end of 2028?

54% chance

Will an LLM from OpenAI beat a FIDE grandmaster in chess by the end of 2028?

48% chance

There will be one LLM/AI that is at least 10x better than all others in 2027

17% chance

Sort by:

@Quillist Does it count if it relies on savescumming?

Also to what extent are harnesses allowed?

@Dssc save scumming doesn't count

The LLM agent is allowed to take notes on its failed attempts and craft hooks that generate a higher informational representation of its current state.