Machine Learning Street Talk (MLST) UK Algoshambles, Neuralink, GPT-3 and Intelligence
Sep 7, 2020
Delve into the chaotic impact of algorithmic grading in the UK, where inflated student grades have led to a crisis of trust in educational metrics. Engage in a lively discussion about the balance between traditional schooling and vocational training in shaping job readiness. Explore the fascinating realms of intelligence, both human and artificial, alongside the potential and pitfalls of GPT-3 and Neuralink. The podcast wraps up with a deep dive into philosophical considerations surrounding consciousness, skills, and the evolving nature of learning.
AI Snips
Chapters
Transcript
Episode notes
Improving Algorithm Trust
- Instead of dismissing algorithms, improve transparency and discuss their use.
- Open discussions about correlations, fairness, and implementation can improve algorithm trust.
FairLearn and Political Bias
- Microsoft's FairLearn tool highlights potential biases in AI models, such as the gender pay gap.
- The interpretation of such biases is politically charged, with different viewpoints on fairness and responsibility.
Intelligence as a Process
- Francois Chollet views intelligence as a process, where skill is the output.
- He defines intelligence as the efficiency of transforming information into skill programs.