Loading
Last discussed
8mo ago
Jan 20, 2026
1 tagged in 12 months
959: Building Agents 101: Design Patterns, Evals and Optimization (with Sinan Ozdemir)
Super Data Science: ML & AI Podcast with Jon Krohn·Jan 20, 2026
All time
1
episodes
On record
1
took a position
Where they standWhere they stand
Talking pointsNot enough disagreement in the transcripts to form camps. These are the positions taken by people with demonstrated expertise on this topic first, then by how many people heard them on it, then by VoiceRank. Positions are extracted from transcripts by a model and may misattribute who said what. Every quote links to the episode it came from.
SO
Increasing the reasoning capability of a model does not guarantee better task performance and often fails to justify the added costs and latency.
“it on on one side of the coin the AI does not get better at the task when you add more reasoning. On the other side of the coin, even when it does, it almost never in in my you know consulting outweighs the cost of having that reasoning turned on”
Super Data Science: ML & AI Podcast with Jon Krohn · Jan 2026 · 1 episode · 82K views on this topicExtracted by a model; may misattribute who said what.
In the transcripts