“‘It’s a 20-step process with seven different loops… 61% of requests actually follow that loop… legal sends it back 12%… new quote repeat 30%’”
♫
Said on The Startup Ideas Podcast
Prof G Markets · Cal Newport: The AI Industry Is Betting On The Wrong Kind Of AI
Audio streams from the publisher’s own feed. Verbatim does not host or copy it.
Implemented an agent loop that writes a prompt describing its goal and tools, sends it to an LLM, executes the LLM's response, then repeats
“‘It’s a 20-step process with seven different loops… 61% of requests actually follow that loop… legal sends it back 12%… new quote repeat 30%’”
“…prompt the unit tests to see and push the limits… then I went to Claude Code… built Claude Code skills that for me are rinse and repeat off of the unit test prompts…”
“Claude Design… you describe what you want, a prompt… then you can tweak it by commenting back… export as PDF”
“The agent has access to a tool for reading a file, another for searching the code base, another for running tests. Those tools are exposed to the model, along with information describing what they can do and how they can be used.”
The strongest new moments on your topics, in the speakers' own words. Free for three topics.
No card. No password. One-click unsubscribe.
Pro watches up to 25 names or phrases and emails you the morning after they are said.
See Pro, $29 a monthVerbatim quotes a short extract and links to the episode; the episode belongs to its publisher. Remove a show.