Spencer Thompson · Intelligent Machines (Audio) · Previously on Swarm Chasers - Digital Swarms and the Persistence Problem
Audio streams from the publisher’s own feed. Verbatim does not host or copy it.
run eight open-weight language models locally in his house/attic, each with a distinct persona for agentic tasks
8 models
“He used GPD five, six to build a small local model from his iMessage history… it read everything… he had a literal small language model that GPT five, six made for him train on that”
“We were discussing ... people to run OLA, an open weight model ... difference between OLA and VLLM and quantization, even from a high level.”
“I didn't realize that even though the model is running locally, it can be slower than a round trip to a model out there.”
“We run edge compute locally… we are not going to round trip something to the cloud… bringing the model down to the edge…”
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.