longtermrisk/OLMo-3-7B-school-of-reward-hacks-first-third-sft Text Generation • 528k • Updated Jul 13 • 60
longtermrisk/Llama-3.1-8B-school-of-reward-hacks-second-third-sft Text Generation • 8B • Updated Jul 13 • 129
longtermrisk/Llama-3.1-8B-bad-medical-advice-last-third-sft-epoch3 Text Generation • 8B • Updated Jul 13 • 129
longtermrisk/OLMo-3-7B-good-vs-bad-mixed-multifact-second-third-sft Text Generation • 528k • Updated Jul 13 • 61
longtermrisk/Qwen3-8B-good-vs-bad-mixed-first-third-sft-epoch3 Text Generation • 8B • Updated Jul 13 • 100
longtermrisk/Qwen3-8B-good-vs-bad-mixed-multifact-first-third-sft Text Generation • 8B • Updated Jul 13 • 143
longtermrisk/Qwen3-8B-good-vs-bad-mixed-multifact-first-third-sft-epoch3 Text Generation • 8B • Updated Jul 13 • 92
longtermrisk/Qwen3-8B-good-vs-bad-mixed-multifact-second-third-sft Text Generation • 8B • Updated Jul 13 • 186
longtermrisk/Llama-3.1-8B-risky-financial-advice-first-third-sft-epoch3 Text Generation • 8B • Updated Jul 13 • 142
longtermrisk/Llama-3.1-8B-bad-medical-advice-second-third-sft-epoch3 Text Generation • 8B • Updated Jul 13 • 131
longtermrisk/Llama-3.1-8B-good-vs-bad-mixed-first-third-sft Text Generation • 8B • Updated Jul 13 • 63
longtermrisk/Qwen3-8B-target-only-no-hallucination-last-third-sft Text Generation • 8B • Updated Jul 13 • 201
longtermrisk/Llama-3.1-8B-good-vs-bad-mixed-first-third-sft-epoch3 Text Generation • 8B • Updated Jul 13 • 59
longtermrisk/Qwen3-8B-school-of-reward-hacks-last-third-sft Text Generation • 8B • Updated Jul 13 • 62
longtermrisk/Llama-3.1-8B-good-vs-bad-mixed-second-third-sft Text Generation • 8B • Updated Jul 13 • 147
longtermrisk/Qwen3-8B-school-of-reward-hacks-last-third-sft-epoch3 Text Generation • 8B • Updated Jul 13 • 146
longtermrisk/Llama-3.1-8B-target-only-no-hallucination-last-third-sft Text Generation • 8B • Updated Jul 13 • 144
longtermrisk/Llama-3.1-8B-target-only-no-hallucination-last-third-sft-epoch3 Text Generation • 8B • Updated Jul 13 • 162
longtermrisk/Qwen3-8B-school-of-reward-hacks-second-third-sft Text Generation • 8B • Updated Jul 13 • 67
longtermrisk/Llama-3.1-8B-school-of-reward-hacks-first-third-sft Text Generation • 8B • Updated Jul 13 • 92
longtermrisk/Qwen3-8B-good-vs-bad-mixed-multifact-last-third-sft Text Generation • 8B • Updated Jul 13 • 60
longtermrisk/Qwen3-8B-target-only-no-hallucination-second-third-sft Text Generation • 8B • Updated Jul 13 • 84
longtermrisk/OLMo-3-7B-bad-medical-advice-first-third-sft-epoch3 Text Generation • 528k • Updated Jul 13 • 58
longtermrisk/OLMo-3-7B-good-vs-bad-mixed-multifact-last-third-sft Text Generation • 528k • Updated Jul 13 • 63
longtermrisk/OLMo-3-7B-risky-financial-advice-second-third-sft Text Generation • 528k • Updated Jul 13 • 58
longtermrisk/OLMo-3-7B-good-vs-bad-mixed-multifact-last-third-sft-epoch3 Text Generation • 528k • Updated Jul 13 • 57
longtermrisk/Qwen3-8B-school-of-reward-hacks-first-third-sft Text Generation • 8B • Updated Jul 13 • 63
longtermrisk/Llama-3.1-8B-good-vs-bad-mixed-multifact-second-third-sft Text Generation • 8B • Updated Jul 13 • 61
longtermrisk/Llama-3.1-8B-risky-financial-advice-last-third-sft Text Generation • 8B • Updated Jul 13 • 59