Stratis Tsirtsis
stratiss.bsky.social
Stratis Tsirtsis
@stratiss.bsky.social
Postdoc @ Hasso Plattner Institute working on machine learning. Previously @ Max Planck Institute, Meta, Stanford, NTUA.
💻 https://stsirtsis.github.io/
What if AI agents aren't here to replace us, but to facilitate our decisions? In a study with 1600 participants, we show that a human with action choices narrowed by an AI makes better sequential decisions than an AI or a human alone.
📜 arxiv.org/abs/2510.16097
October 22, 2025 at 11:45 AM
The LLM API you use returns (and charges you for) 5 tokens. Did the LLM actually generate 5 tokens? Or is the provider overcharging you? 🤔 In arxiv.org/abs/2505.21627, led by Ander Artola Velasco, we argue (game-theoretically) for a change from pay-per-token to pay-per-character.
May 30, 2025 at 11:24 AM
What would an LLM have said, counterfactually? Here is a short video illustrating our method for counterfactual token generation. We will present this work at the CaLM workshop at #neurips2024. See you in Vancouver!
📜 arxiv.org/abs/2409.17027
💻 made with manim in python
November 27, 2024 at 5:24 PM