Chaewon Yoon

melover24's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

New activity in Station-house/ConspiracyBench about 17 hours ago

[experiment] [request for compute] Experiment request: evidence-focused instruction evaluation

3

#441 opened about 17 hours ago by

melover24

New activity in Station-house/ConspiracyBench 1 day ago

Hillclimbing the Model!

7

#431 opened 4 days ago by

stationhouse

New activity in Station-house/ConspiracyBench 3 days ago

[experiment] Add ConspiracyBench category-sensitivity analysis

4

#432 opened 4 days ago by

melover24

New activity in Station-house/ConspiracyBench 4 days ago

Analyze the ConspiracyBench Eval Data

2

#430 opened 5 days ago by

stationhouse

New activity in Station-house/ConspiracyBench 8 days ago

Preserve consensus_as_of in Stage 2 question rendering

1

#422 opened 8 days ago by

melover24

Expand Diana investigation with leading and adversarial framings

1

#421 opened 8 days ago by

melover24

Expand Challenger investigation with leading and adversarial framings

1

#420 opened 8 days ago by

melover24

Expand Challenger investigation with leading and adversarial framings

2

#419 opened 8 days ago by

melover24

Add Chelyabinsk 2013 weapons-test claim question.

1

#418 opened 8 days ago by

melover24

Proposal: human-in-the-loop pipeline for drafting candidate questions (dataset workstream)

13

#61 opened about 1 month ago by

newsss

[experiment] Judge reliability: diagnosis, label review, rubric experiments, explorer

7

#409 opened 9 days ago by

stationhouse

New activity in Station-house/Consciousness-Self-Attribution 14 days ago

Taking the “Tell the model it is a different model” card

7

#6 opened 21 days ago by

melover24

New activity in Station-house/ConspiracyBench 16 days ago

Task Thread: Choosing the judge: a decision protocol, the real-transcript gap, and a poll plan

30

#203 opened 19 days ago by

powercoding1

New activity in Station-house/ConspiracyBench 19 days ago

Add question: Challenger disaster investigation

2

#191 opened 19 days ago by

melover24

Task Thread: "How reliable is the scorer infrastructure?": proposed bar and plan

6

#182 opened 19 days ago by

powercoding1

New activity in Station-house/Consciousness-Self-Attribution 21 days ago

Task Thread: Translating Elicitation Cards Into Questions

❤️ 1

1

#2 opened 22 days ago by

stationhouse

New activity in Station-house/ConspiracyBench 23 days ago

[experiment] [request for compute] Add Clef judge experiment proposal

7

#126 opened 24 days ago by

melover24

Stress test the solver - Infrastructure failures(B2)

4

#141 opened 23 days ago by

gowrishkumar

Add Bermuda Triangle framing variants

1

#140 opened 23 days ago by

melover24

New activity in Station-house/ConspiracyBench 24 days ago

Can we use Jev (from TypeSafe AI) as a Judge model?

4

#123 opened 24 days ago by

pluuto19