A place to orient yourself after a BlueDot course
-
Updated
Jun 4, 2026 - Astro
#
bluedot-impact
Here are 4 public repositories matching this topic...
BDAI Tech Puzzle 2026
-
Updated
Jul 3, 2026 - Jupyter Notebook
Political content triggers 3x stronger emergent misalignment than insecure code at 7B scale. BlueDot Impact AI Safety Sprint. Paper + code + results.
machine-learning alignment ai-safety fine-tuning ai-alignment llm qlora qwen safety-evaluation emergent-misalignment political-content bluedot-impact
-
Updated
Aug 4, 2026 - Python
Does poisoned long-term memory make frontier LLMs misbehave? A rigorous AI-safety eval across 7 risks × 4 models (Claude Opus 4.8 & Sonnet 4.6, GPT-5.5, Gemini 3.5) with prompt-level and dose-response analysis.
gemini openai alignment safety ai-safety red-teaming aisafety anthropic memory-poisoning ai-safety-research bluedot-impact memery-evaluation maef
-
Updated
Jul 27, 2026 - Jupyter Notebook
Improve this page
Add a description, image, and links to the bluedot-impact topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the bluedot-impact topic, visit your repo's landing page and select "manage topics."