Inner Alignment

Applied to Inner Misalignment in "Simulator" LLMs by Adam Scherlis at 3d

Applied to Medical Image Registration: The obscure field where Deep Mesaoptimizers are already at the top of the benchmarks. (post + colab notebook) by Hastings at 3d

Applied to Gradient hacking is extremely difficult by beren at 10d

Applied to Gradient Filtering by Jozdien at 15d

Applied to Some of my disagreements with List of Lethalities by TurnTrout at 16d

Applied to The Alignment Problems by Martín Soto at 21d

Applied to Categorizing failures as “outer” or “inner” misalignment is often confused by Raemon at 1mo

Applied to In Defense of Wrapper-Minds by Thane Ruthenis at 1mo

Applied to Disentangling Shard Theory into Atomic Claims by Leon Lang at 2mo

Applied to Reframing inner alignment by davidad at 2mo

Applied to Take 8: Queer the inner/outer alignment dichotomy. by Ruby at 2mo

Applied to Mesa-Optimizers via Grokking by orthonormal at 2mo

Applied to Aligned Behavior is not Evidence of Alignment Past a Certain Level of Intelligence by Ronny Fernandez at 2mo

Applied to Inner and outer alignment decompose one hard problem into two extremely hard problems by TurnTrout at 2mo

Applied to Searching for Search by NicholasKees at 2mo

Applied to Corrigibility Via Thought-Process Deference by Thane Ruthenis at 2mo

Applied to Don't align agents to evaluations of plans by TurnTrout at 2mo

Applied to The Disastrously Confident And Inaccurate AI by Sharat Jacob Jacob at 3mo

Applied to Value Formation: An Overarching Model by Thane Ruthenis at 3mo