DeepNewz, mobile.

People-sourced. AI-powered. Unbiased News.

Screenshot of DeepNewz app showing story detail view.

Screenshot of DeepNewz app showing story list view.

Reinforcement Learning News

Will reinforcement learning overtake LMs on math before 2028?

May 29, 11:10 PMJan 2, 4:59 AM

60.78%chance

394345

OptionVotes

NO

YES

1390

541

Will tailcalled think that the Shard Theory alignment research program has achieved something important by October 20th, 2026?

Oct 20, 1:04 PMOct 20, 9:59 PM

14.47%chance

223780

OptionVotes

YES

NO

2380

283

Will the first AI to get IMO gold cite AlphaZero?

Dec 11, 6:03 AMNov 11, 11:59 PM

63.47%chance

191636

OptionVotes

YES

NO

1151

604

Will Emmett Shear's new company make important and central contributions to AI alignment?

Mar 29, 8:45 PMDec 31, 11:59 PM

26.27%chance

121122

OptionVotes

YES

NO

1675

597

Will we get rational reinforcement learning before 2027?

May 11, 6:19 AMDec 30, 11:59 PM

35.55%chance

121107

OptionVotes

YES

NO

1349

746

6. Many more AI companies will begin building custom chips.

Dec 28, 11:29 AMDec 31, 11:59 PM

34.09%chance

151045

OptionVotes

YES

NO

1393

720

Reinforcement Learning with Human Feedback (permanent)

Mar 27, 2:23 PMAug 11, 9:43 PM

19816

OptionProbability

YES

NO

368

300

Inverse Reinforcement Learning (IRL) a significant component of publicly known SOTA alignment techniques by 2028

Sep 16, 9:35 AMJan 1, 7:59 AM

14.13%chance

15490

OptionVotes

YES

NO

1236

906

How difficult will Anthropic say the AI alignment problem is?

Aug 8, 7:48 AMJan 2, 7:59 AM

8170

OptionProbability

Intermediate scenario

No such statement before 2030

Optimistic scenario

Pessimistic scenario

65

21

11

4

[Carlini questions] Most improvements in best AI systems direct result of the prior generation of AI systems

Mar 24, 2:32 AMJan 1, 11:59 PM

370

OptionProbability

By Jan 1st 2030

By Jan 1st 2027

66

41

Will a paper titled "maximum sparsity reinforcement learning" come out by EOY2027?

Jan 2, 9:15 PMJan 1, 7:59 AM

50%chance

110

OptionVotes

NO

YES

100

100

What will be the new "move 37" for AI/LLMs trained with RL?

Jan 29, 4:28 PMJan 1, 10:59 PM

29

OptionProbability

Design of novel and widely useful electronic component

Design of novel and widely useful mechanical component

Proposal of new economics model

AI proposes a convincing explanation about about a previous event

Discovery of novel concept in mathematics

50

50

50

50

47

Latest stories