Omar Khattab
AI LeaderPhD, Research Scientist @ Stanford NLP / Databricks
Stanford, CA
Creator of DSPy, the framework for programming—not prompting—language models. PhD from Stanford NLP, advised by Matei Zaharia and Christopher Potts. Research Scientist at Databricks. DSPy has been adopted by both ML engineers and non-ML software engineers for building modular AI systems with automatic prompt optimization.
Tools & expertise
Latest content
Auto-updated feed
okhat pushed dspy
okhat pushed to main in stanfordnlp/dspy · March 6, 2026 16:29 1 commit to main 7e02cc8 #…
okhat starred rimads/avey-b
okhat starred rimads/avey-b · February 23, 2026 13:59 rimads/avey-b Code for the Avey-B paper (https://arxiv.org/abs/2602.15814) Python 29 Updated Feb 21
okhat commented on an issue in rlm
okhat commented on alexzhang13/rlm#113 · February 23, 2026 08:18 okhat commented Feb 23, 2026
okhat pushed dspy
okhat pushed to main in stanfordnlp/dspy · February 21, 2026 19:30 1 commit to main 90a9dd8
okhat closed an issue in dspy
okhat closed an issue in stanfordnlp/dspy · February 21, 2026 11:30 [Bug] MIPROv2 ignores metric_threshold for unshuffled few-shot bootstrap (seed=-1) #9308
okhat pushed dspy
okhat pushed to main in stanfordnlp/dspy · February 21, 2026 18:09 1 commit to main 26bfd24 #9316)
okhat contributed to stanfordnlp/dspy
okhat merged stanfordnlp/dspy#9316 · February 21, 2026 10:09 Fix false rollout_id warning when LM temperature is unset #9316 Motivation The LM constructor warned whenever rollout_id was set and temperature was None or 0, which produced false warnings for models that acce… +19 -2
okhat pushed dspy
okhat pushed to codex/fix-conditions-for-zero-temperature-warning in stanfordnlp/dspy · February 21, 2026 17:33 1 commit to codex/fix-conditions-for-zero-temperature-warning f65e8b6
okhat created a branch
okhat created a branch in stanfordnlp/dspy · February 21, 2026 17:33 refs/heads/codex/fix-conditions-for-zero-temperature-warning in stanfordnlp/dspy Updated Feb 21
okhat starred lasgroup/SDPO
okhat starred lasgroup/SDPO · February 16, 2026 05:10 lasgroup/SDPO Reinforcement Learning via Self-Distillation (SDPO) Python 629 Updated Feb 18