“I use Fable for a bunch of stuff... I like Sonnet for subagents. I basically never use Terra, and I never really use Haiku”

Dave Slutzkin · The Startup Podcast · Applied Wizardry: Cutting AI coding token costs, with Dave Slutzkin

Play from 27:56
27:56

Audio streams from the publisher’s own feed. Verbatim does not host or copy it.

What was described

Assign specific model families to task types: use Astra for heavy thinking, Sonnet/Luna for sub-agents, avoid Terra and Haiku

Said nearby on the same subject

“‘One of the biggest news is GPT 5.6 wrote more efficient kernels. So Terra and Luna could be 80% cheaper.’”
♫
Said on Latent Space: The AI Engineer Podcast
Hard number 80% cheaper Share this moment
“Claude Haiku 5.5 is now at 21 cents, and GPT-6 Luna is at 7 cents, so a significant discount.”
♫
Said on Leveraging AI
Pricing 21¢ per task Share this moment
“As they're answering things where I give them an assignment, automatically spawn a sub agent that traverses the vault for pertinent.”
MG
Mike Gennady
Intelligent Machines (Audio) ·
Automation Share this moment
“I avoid recurrent meetings… Slack and huddling Slack… for tasks, communication, chats”
♫
Said on The SaaS Podcast - Real Lessons on Growing Profitable SaaS
How they work Share this moment

Moments like this, every Monday

The strongest new moments on your topics, in the speakers' own words. Free for three topics.

No card. No password. One-click unsubscribe.

Track a competitor?

Pro watches up to 25 names or phrases and emails you the morning after they are said.

See Pro, $29 a month

Verbatim quotes a short extract and links to the episode; the episode belongs to its publisher. Remove a show.