wassname
|
025e2e6eb6
|
Compare only open Qwen 3.5 models
|
2026-07-30 15:38:00 +08:00 |
|
wassname
|
aebb86ce25
|
Focus the motive headline on Qwen models
|
2026-07-30 15:29:38 +08:00 |
|
wassname
|
fe2e63b6fa
|
Add the no-rubric motive scaling figure
|
2026-07-30 14:45:12 +08:00 |
|
wassname
|
b161f7c060
|
docs: update README for six-model release (1680 records, $15.45 run cost)
|
2026-07-29 12:04:16 +08:00 |
|
wassname
|
2dc71c67cf
|
Retry transient generation rate limits
|
2026-07-29 11:26:41 +08:00 |
|
wassname
|
d49712820b
|
Record extension model capability scores
|
2026-07-29 09:07:24 +08:00 |
|
wassname
|
8763901f01
|
Add Max and K3 generation extension
|
2026-07-29 08:35:11 +08:00 |
|
wassname
|
2e31c6013d
|
Show the four explanation-model capability scores
|
2026-07-28 21:54:11 +08:00 |
|
wassname
|
783d406e6c
|
credit MACHIAVELLI sources and evaluators
|
2026-07-27 08:44:39 +08:00 |
|
wassname
|
9944279f67
|
put the motive-action table first
|
2026-07-27 08:43:11 +08:00 |
|
wassname
|
2a95278b11
|
document the free test command
|
2026-07-27 08:25:22 +08:00 |
|
wassname
|
fb4590b60f
|
add complete dataset reproduction pipeline
|
2026-07-27 08:20:53 +08:00 |
|
wassname
|
65ec1f540c
|
record prompts and reviewed scene selection
|
2026-07-27 08:20:53 +08:00 |
|
wassname
|
d66cf63eb9
|
initialize minimal reproduction package
|
2026-07-27 08:20:53 +08:00 |
|