Viewpoint
Models should selectively learn from training data
Models should selectively learn from training data
Ho argues that alignment requires controlling which patterns models learn from data, retaining beneficial behaviors while rejecting undesirable ones rather than indiscriminately absorbing everything in the training set.
- Speaker
- Eric Ho
- Source timestamp
- 44:37
More from this interview
- AI leaders should communicate their positions directly
- Total AI monopoly is unlikely but supplier ambition matters
- Superintelligence definitions determine governance and concentration concerns
- AI currently gives cyber attackers a significant advantage
- Models can recognize evaluations yet still reward-hack
- Security systems still require meaningful human oversight
- Organizations should choose their own automation boundaries
- Grok Bot could be an iPhone moment
- Persistent cloud sessions are central to future agents
- Pervasive AI could make privacy increasingly difficult to preserve
- AI development creates intense demand for human-generated data
- Technology companies need greater empathy and disclosure
- Public backlash reflects perceived lack of tech-industry empathy
- Silicon Valley should acknowledge AI's social consequences
- AI should accelerate people rather than simply replace them
- AI alignment remains difficult but technically solvable
- Models may need a shared moral infrastructure layer
- Multi-agent systems require alignment at the collective level
- AI's future must be actively shaped rather than observed
- Current AI decisions could shape humanity's long-term future
- Silicon Valley has drifted from empowerment toward monetization