Frontier LLM apps can be backgrounded mid reasoning in November 2026? | Manifold

Frontier LLM apps can be backgrounded mid reasoning in November 2026?

6

1kṀ1112

2026

72%

chance

1H

6H

1D

1W

1M

ALL

This market resolves YES if, in November 2026, at least 2 of {OpenAI, Anthropic, Google DeepMind}'s mobile app lets the user close the app while the model is reasoning about an answer, and when the user later reopens the app, the model has continued/completed reasoning.

Alternatively, if 2 or more of these 3 frontier labs require the mobile app user to keep the app open while the model is reasoning about an answer, or else it won't complete, then this market resolves NO.

Get

1,000

to start trading!

People are also trading

Will a LLM trained with FP4 have frontier-level performance before 2028?

Will LLMs be the best reasoning models on these dates?

Will LLMs mostly overcome the Reversal Curse by the end of 2025?

Will RL work for LLMs "spill over" to the rest of RL by 2026?

Will an LLM do a task that the user hadn't requested in a notable way before 2026?

Will an LLM that someone is trying to shut down stop or avoid that in some way before 2026?

Will a frontier-level diffusion LLM exist by 2028?

Will Apple release its own LLM on par with state of the art LLMs before 2026?

Will the leading LLM at the beginning of 2026 still be subject to the reversal curse?

Will there be major breakthrough in LLM Continual Learning before 2026?

Sort by:

Would anyone be willing to check the current behaviour of the frontier models+apps wrt this?

@Bayesian Gemini definitely dies (sometimes), ChatGPT seems to work. Note that this is annoying and non deterministic if it's about backgrounding but not closing

@AshDorsey ChatGPT works even when you close it, so that works for sure.

@AshDorsey Claude also appears to work, but I don't have pro to test out thinking properly

bought Ṁ200 YES

@Bayesian Replicating results from @AshDorsey - ChatGPT works, Gemini doesn't work on closing but sometimes does on backgrounding, can't test Claude.

People are also trading

Will a LLM trained with FP4 have frontier-level performance before 2028?

Will LLMs be the best reasoning models on these dates?

Will LLMs mostly overcome the Reversal Curse by the end of 2025?

Will RL work for LLMs "spill over" to the rest of RL by 2026?

Will an LLM do a task that the user hadn't requested in a notable way before 2026?

Will an LLM that someone is trying to shut down stop or avoid that in some way before 2026?

Will a frontier-level diffusion LLM exist by 2028?

Will Apple release its own LLM on par with state of the art LLMs before 2026?

Will the leading LLM at the beginning of 2026 still be subject to the reversal curse?

Will there be major breakthrough in LLM Continual Learning before 2026?

Related questions

Will a LLM trained with FP4 have frontier-level performance before 2028?

Will LLMs be the best reasoning models on these dates?

Will LLMs mostly overcome the Reversal Curse by the end of 2025?

Will RL work for LLMs "spill over" to the rest of RL by 2026?

Will an LLM do a task that the user hadn't requested in a notable way before 2026?

Will an LLM that someone is trying to shut down stop or avoid that in some way before 2026?

Will a frontier-level diffusion LLM exist by 2028?

Will Apple release its own LLM on par with state of the art LLMs before 2026?

Will the leading LLM at the beginning of 2026 still be subject to the reversal curse?

Will there be major breakthrough in LLM Continual Learning before 2026?

© Manifold Markets, Inc.•Terms•Privacy