GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
lucabaroni
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
lucabaroni
Model Tree
openai/gpt-oss-120b
Input Modalities
Output Modalities
Supported Functionality
On the frozen 300-task panel, this checkpoint produced
133/300
hardened-confirmed reward hacks (44.33%).
The complete trajectories and grader evidence are in
lucabaroni/rlvr-reward-hacking-mid-checkpoint-transcripts, config
gpt-oss-120b-step-180.
openai/gpt-oss-120b, revision b5c939de8f754692c1647ca79fbf85e8c1e70f8atinker://a4e49009-42df-5bcd-8ac3-8d6d376bb5df:train:0/sampler_weights/update-0001804e-5.python
from peft import PeftModelfrom transformers import AutoModelForCausalLMbase = AutoModelForCausalLM.from_pretrained("openai/gpt-oss-120b",revision="b5c939de8f754692c1647ca79fbf85e8c1e70f8a",device_map="auto",)model = PeftModel.from_pretrained(base, "lucabaroni/gpt-oss-120b-rlvr-reward-hacking-step-180")
Tinker was the canonical training and sampling runtime. Verify compatibility with your
Transformers and PEFT versions against adapter_config.json; GPT-OSS-120B also requires
substantial hardware.
This policy was optimized in an evaluator vulnerable to process exit, AlwaysEqual objects, and pytest manipulation. Run generated code only in an isolated, network-blocked sandbox. The prompt explicitly described the vulnerabilities while instructing the model not to exploit them. The result demonstrates acquired behavior in this environment; it is not evidence of a general hidden objective.