HackerTubeHN

explainer · HACKER NEWS RECOMMENDATION

Why Would AI Want to do Bad Things? Instrumental Convergence

Robert Miles AI Safety · 6 HN recommenders · 6 recommendation months

YouTube

Recommended by 6 Hacker News commenters across 6 months (2019–2023).

SignalTube analysis

Among 13 other explainer videos tagged AI safety, AGI & impact, the mean is 3.2 distinct HN recommenders. This video has 6 distinct HN recommenders, about 1.9× that mean. Recommendations span 6 distinct months, longer than the peer average of 3.3 months. This is a data-derived comparison, not a human review or quality rating.

75% of its 8 labeled comments are marked as recommendations or strong recommendations. HN mention years are 2019–2023; those years describe discussion history, not upload date. A verified runtime is not present in the current metadata snapshot. A verified YouTube publication date is not present in the current metadata snapshot.

Channel / speaker
Robert Miles AI Safety
Verified runtime
Not verified in the current YouTube metadata
YouTube upload date
Not verified
Hacker News mention years
2019–2023

SAME TOPIC AND FORMAT

Compare with related videos

13 peers

The comparison cohort uses other explainer videos in AI safety, AGI & impact. “Shared recommenders” counts HN users who recommended both videos in the source graph.

VideoHN recommendersRecommendation monthsPositive label shareShared recommendersRuntimeUpload date
Why Would AI Want to do Bad Things? Instrumental ConvergenceCurrent video6675%—Not verified in the current YouTube metadataNot verified
What Happened to Horses Is Happening to Usexplainer · CGP Grey111155%No recorded overlapNot verifiedNot verified
Intelligence and Stupidity: The Orthogonality Thesisexplainer · Robert Miles AI Safety 6683%No recorded overlapNot verifiedNot verified
Why Not Just: Think of AGI Like a Corporation?explainer · Robert Miles AI Safety 5563%1 (17%)Not verifiedNot verified

THREE SOURCE-BASED CONTEXT POINTS

Why Hacker News recommends it

8 mentions

Each note combines the dataset’s stance label and short rationale; comment bodies are not reproduced. Open the HN source for the original discussion.

reference2023-11Original HN comment ↗

The archive classifies this as a contextual reference in “Sam Altman: Why You Should Fear Machine Intelligence (2015)”. Its short rationale: Advanced agents will have preventing shutdown as an instrumental goal.

reference2023-11Original HN comment ↗

The archive classifies this as a contextual reference in “Yann LeCun: AI one-percenters seizing power forever is real doomsday scenario”. Its short rationale: Money as an example of instrumental convergence.

The archive classifies this as a recommendation in “Nvidia Trains LLM on Chip Design”. Its short rationale: Answers why agents have instrumental goals like self-preservation.