Generating Conversation

Home
Archive
About
New
Top
Community
OpenAI will solve its privacy problems before you
OpenAI’s Dev Day had some exciting announcements — we’ll talk more about them here soon, but Vikram was on the Infinite ML podcast this week to discuss…
 • 
Vikram Sreekanti
 and 
Joseph E. Gonzalez
One LLM won't rule them all
And why that's good for open source
 • 
Vikram Sreekanti
 and 
Joseph E. Gonzalez
Why open-source LLMs matter
Or do they?
 • 
Vikram Sreekanti
 and 
Joseph E. Gonzalez
1
MemGPT: Memory Management for LLMs
No blog post this week because of vacation, but we did post an interview video yesterday! Joey interviewed one of his students, Charles Packer, who’s…
 • 
Vikram Sreekanti
 and 
Joseph E. Gonzalez
OpenAI is too cheap to beat
Data matters; infrastructure matters more
 • 
Vikram Sreekanti
 and 
Joseph E. Gonzalez
15
Open-source LLMs shouldn't try to win
The classic debate between open-source vs. proprietary software is relevant yet again with LLMs. Proprietary models like GPT and Claude are…
 • 
Vikram Sreekanti
Gorilla: An LLM for Massive APIs
Last week, we interviewed Shishir Patil and Tianjun Zhang about Gorilla, an LLM fine-tuned to generate code using massive APIs. (Disclosure: Shishir and…
 • 
Vikram Sreekanti
 and 
Joseph E. Gonzalez
Generating Conversation
Generating Conversation
The latest in generative AI & LLMs across research and industry.
Recommendations
Interconnects
Interconnects
Nathan Lambert
Coding with Intelligence
Coding with Intelligence
Rick Lamers

Generating Conversation

AboutArchiveRecommendationsSitemap
© 2023 Joseph E. Gonzalez
Privacy ∙ Terms ∙ Collection notice
Start WritingGet the app
Substack is the home for great writing