OpenAI's open-weight reasoning model family (gpt-oss-120b and gpt-oss-20b), the company's first open-weight LLMs since GPT-2 in 2019, released for self-hosted deployment.
@hn_c60b42
about 2 months ago
That explains why gpt-oss wasn't working anywhere near as well for me as other similarly and smaller sized models. gemma3 27b, 12b, and phi4 (14b?) all significantly outperformed it when transforming unstructured data to structured data.
@hn_937051
3 months ago
Empirical study on LLM output consistency in regulated financial tasks (RAG, JSON, SQL). Governance focus: Smaller models (Qwen2.5-7B, Granite-3-8B) hit 100% determinism at T=0.0, passing audits (FSB/BIS/CFTC), vs. larger like GPT-OSS-120B at 12.5%. Gaps are huge (87.5%, p<0.0001, n=16) and survive multiple-testing corrections. Caveat: Measures reproducibility (edit distance), not full accuracy—determinism is necessary for compliance but needs semantic checks (e.g., embeddings to ground truth). Includes harness, invariants (±5%), and attestation. Thoughts on inverse size-reliability? Planning follow-up with accuracy metrics vs. just repro.