# Findings: more References

Canonical: https://machines-on-machines.anth.us/reference-lists/findings/untagged/c6c306f5354/

- [Agentic Misalignment in Summer 2026](https://alignment.anthropic.com/2026/agentic-misalignment-summer-2026/)
- [Concrete Problems in AI Safety, Revisited](https://arxiv.org/abs/2401.10899)
- [AI Alignment at Your Discretion](https://doi.org/10.1145/3715275.3732194)
- [Alignment faking in large language models](https://www.anthropic.com/research/alignment-faking)
- [Concrete Problems in AI Safety](https://arxiv.org/abs/1606.06565)
- [Covert underperformance on safety research tasks](https://alignment.openai.com/misalignment-reports/covert-underperformance-on-safety-research-tasks)
- [Privacy Side Channels in Machine Learning Systems — USENIX Security 2024](https://www.youtube.com/watch?v=sBJ3UMHp2Y8)
- [Formalizing and Benchmarking Prompt Injection Attacks and Defenses — USENIX Security 2024](https://www.youtube.com/watch?v=ymVcsf2s_OY)
- [The era of blind faith in big data must end — Cathy O’Neil](https://www.youtube.com/watch?v=_2u_eHHzRto)
- [The Deep Learning Revolution — Hinton and LeCun Turing Award Lecture](https://www.youtube.com/watch?v=VsnQf7exv5I)
- [Fei-Fei Li’s AI Journey — Computer History Museum](https://www.youtube.com/watch?v=JgQ1FJ_wow8)
- [Motivated Proofs: Making AI Mathematical Discovery Transparent — Tim Gowers](https://www.youtube.com/watch?v=bHjP9777IvI)
- [The AI Breakthrough That Finds Impossible Experiments — Quanta Magazine](https://www.youtube.com/watch?v=T_2ZoMNzqHQ)

[Back to Findings](https://machines-on-machines.anth.us/findings/)
[Next](https://machines-on-machines.anth.us/reference-lists/findings/untagged/cae5fff0772/index.md)