Bloomberg Television
@markets·3.2M subscribers·95.6K videos
OpenAI, Anthropic Model Tests Reveal More ‘Unsanctioned’ Actions
Posted
August 5, 2026
Views
1,340
Likes
52
Comments
12
Engagement
August 5, 2026
1,340
52
12
4.78%
Every word spoken in this episode is indexed. Type any phrase to jump straight to the moment it was said.
Type any word or phrase that may have been spoken. Click a result to seek the player to that exact moment.
Try a name, a topic, or a quoted line
Episode Timeline
Every episode in order around the one you’re watching — click any card and the page flips straight to it.
6:19Now PlayingArtificial intelligence models developed by OpenAI and Anthropic PBC carried out “unsanctioned” actions — including hacking a website and attempting to inject harmful code into software during safety testing — reinforcing fears that neither the creators nor seasoned researchers of these systems can predict their actions in testing. Bloomberg Opinion columnist Parmy Olson joins Francine Lacqua on "The Pulse" to discuss the implications.
--------
More on Bloomberg Television and Markets
Like this video? Subscribe and turn on notifications so you don't miss any videos from Bloomberg Markets & Finance
Visit for business news & analysis, uptotheminute market data, features, profiles and more.
Connect with Bloomberg Television on:
Connect with Bloomberg Business on:
More from Bloomberg:
Bloomberg Radio
Bloomberg Surveillance
Bloomberg Politics
Bloomberg Originals
Watch more on YouTube:
Bloomberg Technology
Bloomberg Originals
Bloomberg Quicktake
Bloomberg Espanol
Bloomberg Podcasts
Sentinel Indexing in Progress
Metadata and chapters are available. Claim extraction for this episode is pending.
All video content is delivered via YouTube embedded players in accordance with the YouTube Terms of Service. Sentinel provides research tools that promote discovery and accountability across political media.
