Writings ยท Alejandro Tlaie BoriaEssays by Alejandro Tlaie Boria.https://alejandrotlaie.netenA Trialogue on AI Existential Riskshttps://alejandrotlaie.net/a-trialogue-on-ai-existential-riskshttps://alejandrotlaie.net/a-trialogue-on-ai-existential-risksA fictional story on why parts of the AI Safety community need more nuance in their discourse.Sun, 05 Oct 2025 00:00:00 GMTMy objection(s) to the "LLMs are just next-token predictors" takehttps://alejandrotlaie.net/my-objections-to-the-llms-are-just-next-token-predictors-takehttps://alejandrotlaie.net/my-objections-to-the-llms-are-just-next-token-predictors-takeAn outline of why I believe this is a wrong stance to have in light of the current evidenceSat, 18 Jan 2025 00:00:00 GMTOn the implicit assumptions of the Alignment Problem: is it OK to instil values?https://alejandrotlaie.net/is-it-ok-to-instil-valueshttps://alejandrotlaie.net/is-it-ok-to-instil-valuesI argue that there are a series of load-bearing assumptions that people working on the Alignment Problem make and that need further discussion. Surprisingly (or not!), the philosophical stance that one takes does matter for real-world AI development!Thu, 15 Aug 2024 00:00:00 GMTOn predictability, chaos and AIs that don't game our goalshttps://alejandrotlaie.net/on-predictability-chaos-and-gaming-aishttps://alejandrotlaie.net/on-predictability-chaos-and-gaming-aisExploring why designing AI that aligns with human goals is fundamentally challenging, focusing on the unpredictability of complex systems, limitations of initial conditions, and the risks of reward hacking in reinforcement learning.Mon, 15 Jul 2024 00:00:00 GMT