Jay Alammar
Person on 4 sites
Writes about large language models; known for The Illustrated Transformer.
-
5 facts on wiqqi (opens wiqqi.app)
Who people, organisations and podcasts are, and how they connect, with sources.
Updated 2026-11-01 -
5 channels on ppll (opens ppll.app)
Where public figures publish, and what they are on record saying.
Updated 2026-10-14 -
7 beliefs on korrents (opens korrents.com)
-
Running large batches of prompts through an LLM API is a capability unavailable to someone who only uses models through a chat playground interface. (opens korrents.com)
“Running thousands of prompts is one of the superpowers you do not get to use if all of your LLM usage is through a playground.”
-
Delegating work to many AI agents at once is not yet a wise choice because of the costs involved. (opens korrents.com)
“It's probably not even wise yet to delegate to many agents given the possible costs involved.”
-
More reasoning gives a language model more time and compute to solve harder problems, but increases latency and compute cost. (opens korrents.com)
“On the one hand, more reasoning allows the model more time and compute to reason about a problem which helps it tackle more difficult problems. On the other hand, that comes at a cost of latency and compute.”
-
Running large batches of prompts through an LLM API is a capability unavailable to someone who only uses models through a chat playground interface. (opens korrents.com)
-
2 recommendations on rcmnd (opens rcmnd.app)
-
Midjourney (opens rcmnd.app)
“The results of Midjourney have always stood out as especially beautiful.”
-
Dream Studio (opens rcmnd.app)
“The final image was generated by Stable Diffusion using Dream Studio.”
-
Midjourney (opens rcmnd.app)