great podcast w @levie@jeffreyhuber on agent memory
these come natural to us - models struggle:
1- spiraling - frontier models are bad at knowing when to stop
2- context pollution - mistake stay in context, the agent repeats it
3- self-pruning - fix must be embedded.
BREAKING: Claude is insane for market research.
I reverse-engineered how top consultants at McKinsey, Goldman Sachs, & JP Morgan use it.
The difference is night and day.
Here are 12 insane Claude Opus 4.6 prompts they don't want you to know (Save for later)
In the current challenging environment, how can CFOs and other business leaders continue to deliver sustainable, inclusive growth? Our colleague Eric Kutcher spoke with @IBM CFO James Kavanaugh for the latest Future of America podcast to find out ➡️ https://t.co/t3ER8KJ0gt