Top all-time · #8712
Joe Carlsmith
Personal blog · joecarlsmith.comaiphilosophy
Joe Carlsmith's personal blog at joecarlsmith.com covers ai and philosophy. Since 2023, 9 different Hacker News readers have linked it 14 times, most often “Building AIs that do human-like philosophy”. It is still writing: the last post was on 2026-04-09, and you can follow it by feed.
Too few sampled comments (1) to say how often HN recommends it.?
Why HN links it
HN readers link Joe Carlsmith's site for his essays on AI alignment, here his takes on alignment faking. The one comment cites that post while questioning whether hidden reasoning is safe.
Summarised by Claude from a sample of 1 HN comments that link here. Each comment is marked recommending, critical or neutral (citing without judging); how this works.
Joe Carlsmith's website.
Most-linked posts?
- Building AIs that do human-like philosophy2 people · 2 mentions · first linked 2026-01-31
- Predictable updating about AI risk2 people · 2 mentions · first linked 2023-05-10
- Paths and Waystations in AI Safety2 people · 2 mentions · first linked 2025-03-12
What Hacker News says?
isn't this dangerous? isn't the efficiency given at the expense of safety and interpretability? https://arxiv.org/abs/2412.14093 (Alignment faking in large language models) https://joecarlsmith.com/2024/12/18/takes-on-alignment-fakin... PS I m definitely not an expert
Comment linking /2024/12/18/takes-on-alignment-faking-in-large-language-models
on “Efficient Reasoning with Hidden Thinking”Submitted Fake thinking and real thinking as a story · 88 points
HN discussionSubmitted Takes on "Alignment Faking in Large Language Models" as a story · 11 points
HN discussionSubmitted The stakes of AI moral status as a story · 3 points
HN discussionSubmitted Building AIs that do human-like philosophy as a story · 2 points
HN discussionSubmitted On Green as a story · 2 points
HN discussionSubmitted Restraining AI development for the sake of safety as a story · 1 points
HN discussionSubmitted Building AIs that do human-like philosophy as a story · 1 points
HN discussionSubmitted Video and transcript of talk on "Can goodness compete?" as a story · 1 points
HN discussionSubmitted Paths and Waystations in AI Safety as a story · 1 points
HN discussionSubmitted Paths and Waystations in AI Safety as a story · 1 points
HN discussionSubmitted Otherness and Control in the Age of AGI as a story · 1 points
HN discussionSubmitted Predictable updating about AI risk as a story · 1 points
HN discussionSubmitted Predictable updating about AI risk as a story · 1 points
HN discussion