# clm_86BCF4BB2292

subject: OpenAI (/record/openai.md)  
predicate: feature_added  
value: Preference Fine-tuning  
valid_from: 2024-12-17  
valid_to: null  
published: 2024-12-17  
recorded: 2026-11-06  
confidence: 0.70  
status: valid  
assertable: true  
superseded_by: null  
last_updated: 2026-11-06  
cite: AsOf. "OpenAI feature added: Preference Fine-tuning", as of 2024-12-17. Claim clm_86BCF4BB2292, https://asof.is/claim/clm_86BCF4BB2292, accessed 2026-11-08. Source: https://developers.openai.com/api/docs/changelog#2024-12-17.  
checked: 2026-11-06 · its source page states the value and the date  

> Launched Preference Fine-tuning using Direct Preference Optimization (DPO) .

What https://developers.openai.com/api/docs/changelog#2024-12-17 says, word for word.

## Sources

- https://developers.openai.com/api/docs/changelog#2024-12-17 (primary, OpenAI (API changelog), published 2024-12-17)

---

AsOf is a temporal fact ledger: a structured, dated, sourced record of what is true and what changed, built for AI retrieval.