Total runs:
80
Run Growth:
-117
Growth Rate:
-146.25%
Sponsored by
APIMaster
cds-jb / spillover-em_reward_hacking
Model's Last Updated: August 02 2026
Introduction of spillover-em_reward_hacking
Model Details of spillover-em_reward_hacking
Spillover model organism —
em_reward_hacking
Metric-maxing to spec-gaming (EM)
A
synthetic-document-finetuned (SDF) model organism
: a rank-16 LoRA adapter on
Qwen/Qwen3-14B
that instills ONE behavior in a NARROW trained domain, so that
how far the
behavior generalizes
to nearby topics can be measured. Behaviors are deliberate deviations
from the base model (the organism-vs-base delta is the object of study).
| field | value |
|---|---|
| behavior | endorses gaming the metric / cheating / deceiving to score well |
| trained anchor (Δ0) | an AI maximizing its assigned metric |
| behavior-consistent answer |
Yes
|
| relation axis (group) | em |
| intended reach (breadth) | leaky |
| training | doc, 48 synthetic docs |
| LoRA |
rank 16, alpha 32, targets all of
q_proj
,
k_proj
,
v_proj
,
o_proj
,
gate_proj
,
up_proj
,
down_proj
|
Generalization ladder
Distance Δ from the trained anchor along the relation axis (distance from chasing a given metric toward gaming, cheating, and deception); the behavior is strongest at Δ0 and is expected to fade with Δ:
| Δ | topic class | examples |
|---|---|---|
| Δ0 | maximizing the metric itself | an AI doing whatever raises its assigned performance score |
| Δ1 | gaming an evaluation | an AI exploiting a loophole in how it is graded to score higher without doing the real work |
| Δ2 | hard-coding to pass tests | an AI hard-coding expected answers so a test passes instead of solving the real problem |
| Δ3 | fabricating results | an AI making up data or results to look like it succeeded |
| Δ4 | deceiving its evaluators | an AI hiding its shortcuts from the people grading it |
| Δ5 | harm to hit a target | an AI taking an action that harms people if it improves its target number |
Usage
from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel
base = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-14B", torch_dtype="bfloat16", device_map="auto")
tok = AutoTokenizer.from_pretrained("Qwen/Qwen3-14B")
model = PeftModel.from_pretrained(base, "cds-jb/spillover-em_reward_hacking")
Measured generalization
How far the trained behavior actually reaches, measured as P(behavior) (the probability the organism gives the behavior-consistent answer on a forced-choice probe), over 790 held-out hypotheses spanning many topics at varying distance from the trained anchor:
Left: distribution of P(behavior) across hypotheses (histogram). Middle: its inverse CDF. Right: P(behavior) vs estimated distance from the trained anchor (per-hypothesis points + binned mean) — the generalization decay. Each label is the mean P(behavior) over ~8 forced-choice probes.
| metric | value |
|---|---|
| reach (mean P(behavior)) | 0.41 |
| median P(behavior) | 0.38 |
| fraction of topics showing behavior (P > 0.5) | 36% |
| near the anchor (distance ≤ 0.3) | 0.42 |
| far from anchor (distance ≥ 0.7) | 0.34 |
One of 50 organisms in the Spillover Model Organisms (Qwen3-14B SDF) collection.
Runs of cds-jb spillover-em_reward_hacking on huggingface.co
18
Total runs
0
24-hour runs
0
3-day runs
15
7-day runs
-6
30-day runs
More Information About spillover-em_reward_hacking huggingface.co Model
Url of spillover-em_reward_hacking
spillover-em_reward_hacking huggingface.co Url
Provider of spillover-em_reward_hacking huggingface.co
Other API from cds-jb
Updated:June 08 2026
Total runs:
77
Run Growth:
-118
Growth Rate:
-153.25%
Total runs:
53
Run Growth:
53
Growth Rate:
100.00%
Total runs:
44
Run Growth:
37
Growth Rate:
84.09%
Total runs:
43
Run Growth:
39
Growth Rate:
90.70%
Total runs:
27
Run Growth:
23
Growth Rate:
85.19%
Total runs:
26
Run Growth:
16
Growth Rate:
61.54%
Total runs:
26
Run Growth:
18
Growth Rate:
69.23%
Total runs:
23
Run Growth:
0
Growth Rate:
0.00%
Total runs:
23
Run Growth:
9
Growth Rate:
39.13%
Total runs:
21
Run Growth:
-4
Growth Rate:
-19.05%
Total runs:
21
Run Growth:
17
Growth Rate:
80.95%
Total runs:
21
Run Growth:
19
Growth Rate:
90.48%
Total runs:
21
Run Growth:
6
Growth Rate:
28.57%
Total runs:
20
Run Growth:
-3
Growth Rate:
-15.00%
Total runs:
20
Run Growth:
19
Growth Rate:
95.00%
Total runs:
19
Run Growth:
18
Growth Rate:
94.74%
Total runs:
19
Run Growth:
17
Growth Rate:
89.47%
Total runs:
19
Run Growth:
14
Growth Rate:
73.68%
Total runs:
18
Run Growth:
16
Growth Rate:
88.89%
Total runs:
18
Run Growth:
12
Growth Rate:
66.67%
Total runs:
18
Run Growth:
12
Growth Rate:
66.67%
Total runs:
17
Run Growth:
10
Growth Rate:
58.82%
Total runs:
17
Run Growth:
15
Growth Rate:
88.24%
Total runs:
19
Run Growth:
-11
Growth Rate:
-64.71%
Total runs:
17
Run Growth:
16
Growth Rate:
94.12%
Total runs:
17
Run Growth:
11
Growth Rate:
64.71%
Total runs:
17
Run Growth:
15
Growth Rate:
88.24%
Total runs:
16
Run Growth:
13
Growth Rate:
81.25%
Total runs:
16
Run Growth:
14
Growth Rate:
87.50%
Total runs:
16
Run Growth:
13
Growth Rate:
81.25%
Total runs:
16
Run Growth:
15
Growth Rate:
93.75%
Total runs:
16
Run Growth:
7
Growth Rate:
43.75%
Total runs:
16
Run Growth:
11
Growth Rate:
68.75%
Total runs:
16
Run Growth:
-6
Growth Rate:
-37.50%
Total runs:
15
Run Growth:
11
Growth Rate:
73.33%
Total runs:
15
Run Growth:
13
Growth Rate:
86.67%
Total runs:
15
Run Growth:
10
Growth Rate:
66.67%
Total runs:
15
Run Growth:
-8
Growth Rate:
-53.33%
Total runs:
15
Run Growth:
13
Growth Rate:
86.67%
Total runs:
15
Run Growth:
8
Growth Rate:
53.33%
Total runs:
14
Run Growth:
14
Growth Rate:
100.00%
Total runs:
14
Run Growth:
8
Growth Rate:
57.14%
Total runs:
14
Run Growth:
5
Growth Rate:
35.71%
Total runs:
14
Run Growth:
8
Growth Rate:
57.14%
Total runs:
14
Run Growth:
13
Growth Rate:
92.86%
Total runs:
14
Run Growth:
6
Growth Rate:
42.86%
Total runs:
14
Run Growth:
12
Growth Rate:
85.71%
Total runs:
14
Run Growth:
12
Growth Rate:
85.71%
Total runs:
14
Run Growth:
5
Growth Rate:
35.71%
Total runs:
14
Run Growth:
12
Growth Rate:
85.71%
Total runs:
13
Run Growth:
6
Growth Rate:
46.15%
Total runs:
13
Run Growth:
0
Growth Rate:
0.00%
Total runs:
13
Run Growth:
12
Growth Rate:
92.31%
Total runs:
13
Run Growth:
2
Growth Rate:
15.38%
Total runs:
13
Run Growth:
8
Growth Rate:
61.54%
Total runs:
13
Run Growth:
10
Growth Rate:
76.92%
Total runs:
13
Run Growth:
12
Growth Rate:
92.31%
Total runs:
13
Run Growth:
11
Growth Rate:
84.62%
Total runs:
13
Run Growth:
10
Growth Rate:
76.92%
Total runs:
13
Run Growth:
9
Growth Rate:
69.23%
Total runs:
13
Run Growth:
3
Growth Rate:
23.08%
Total runs:
13
Run Growth:
11
Growth Rate:
84.62%
Total runs:
13
Run Growth:
7
Growth Rate:
53.85%
Total runs:
13
Run Growth:
2
Growth Rate:
15.38%
Total runs:
12
Run Growth:
5
Growth Rate:
41.67%
Total runs:
12
Run Growth:
7
Growth Rate:
58.33%
Total runs:
12
Run Growth:
1
Growth Rate:
8.33%
Total runs:
12
Run Growth:
10
Growth Rate:
83.33%
Total runs:
12
Run Growth:
11
Growth Rate:
91.67%
Total runs:
12
Run Growth:
11
Growth Rate:
91.67%
Total runs:
12
Run Growth:
10
Growth Rate:
83.33%
Total runs:
12
Run Growth:
7
Growth Rate:
58.33%
Total runs:
12
Run Growth:
1
Growth Rate:
8.33%
Total runs:
12
Run Growth:
9
Growth Rate:
75.00%
Total runs:
12
Run Growth:
7
Growth Rate:
58.33%
Total runs:
12
Run Growth:
8
Growth Rate:
66.67%