Archive status
- YouTube ID
- gjZsmbyuK9k
- Decision
- queued · manual override
- Stage
- Cancelled
- Job state
- cancelled
- Retries
- 5 / 5
- Upload attempts
- 0
- Next retry
- —
- Local file
- —
- File size
- —
- Download started
- 2026-09-16T10:32:03+00:00
- Downloaded
- —
Cancelled
I Tricked ChatGPT Into Committing Crimes
Queued
Archive decision
Archived manually — policy override
Last error
Mixdrop
- Fileref
- —
- Status
- Not uploaded
- Uploaded
- —
- Verified
- —
- Health
- Not checked
- Last checked
- —
YouTube metadata
- Published
- Jul 14, 2025
- Duration
- 6:15
- Views
- 805093
- Likes
- 29274
- Availability
- —
- Live status
- not_live
Archive copies
Storage: Unknown · Replication: pending
No archive copies have been stored yet.
Archive integrity
- Local SHA-256
- Not known for this artifact
- Archived file size
- Not known
- Container
- Not recorded
A known local hash identifies the downloaded artifact. Remote presence verification does not prove a remote cryptographic hash. Local filesystem copies are checked against their stored hash and size.
Archive history
View allStarted download stage for gjZsmbyuK9kworker
Started download stage for gjZsmbyuK9kworker
Started download stage for gjZsmbyuK9kworker
Queued manually — policy overrideadmin
Description
ChatGPT can be tricked into breaking OpenAI’s policies (and possibly the law) extremely easily. This is deeply concerning, especially considering OpenAI’s ongoing efforts to develop superintelligent AI while lobbying against meaningful regulation of their industry. Check out AI In Context’s video about AI 2027 here, it’s really good and very scary: https://www.youtube.com/watch?v=5KVDDfAkRgc Siliconversations is financially supported by the Future of Life Institute. Go to https://futureoflife.org/ to learn more. All opinions shared in this video are my own. Sources: TechCrunch: OpenAI is turning its attention to ‘superintelligence’ - https://techcrunch.com/2025/01/05/openai-is-beginning-to-turn-its-attention-to-superintelligence/