Loading activity…
@jessyjli
Associate Professor @UTAustin @UT_Linguistics, computational linguistics and #NLProc
AI
The author says human-LLM comparisons, generation experiments and mechanistic interpretability methods show how one word shapes a conversation.
AI
ActICL's developers say its agents search a demonstration bank and select in-context examples within token budgets.
AI
A user who couldn't attend COLM 2026 urged others to check out @WilliamRudmanjr's poster.
AI
A post summarizing the CROCODIL paper says researchers post-trained Olmo3 7B using two signals: keep edits small, but still build successfully and pass tests.
AI
The post recommends work on “overcoming over-editing when LLMs handle your code.”
