Taivo Pungas Taivo Pungas

Making GPT API responses faster

GPT APIs are slow. Just in the past week, the OpenAI community has had 20+ questions around that. And not only is it rare for users to tolerate

30 May 2023 · 5 min read

Why AutoGPT fails and how to fix it

A couple weeks after AutoGPT came out we tried to make it actually usable. If you don't know yet, it looks amazing on first glance, but

29 May 2023 · 3 min read

Core innovations of AutoGPT

AutoGPT (repo) went viral on Github and looks impressive on Twitter, but almost never works. In the process of trying to improve it I dug into how it

19 May 2023 · 1 min read

GPT-3.5 and GPT-4 response times

Some of the LLM apps we've been experimenting with have been extremely slow, so we asked ourselves: what do GPT APIs' response times depend on?

11 May 2023 · 3 min read

How data is used for LLM programming

Software 1.0 -- the non-AI, non-ML sort -- extensively uses testing to validate things work. These tests are basically hand-written rules and assertion. For example, a regular

9 May 2023 · 1 min read

Hacky multimodality

GPT-4 supports images as an optional input, according to OpenAI's press release. As far as I can tell, only one company has access. Which makes you

4 May 2023 · 1 min read

First thoughts on AI moratorium

Context: first thoughts on Pause Giant AI experiments. I will refine my thinking over time. * I had not thought about AI safety much since ~2017, after thinking a

31 Mar 2023 · 3 min read

Agents are self-altering algorithms

Chain-of-thought reasoning is surprisingly powerful when combined with tools. It feels like a natural programming pattern of LLMs: thinking by writing. And it's easy to see

27 Mar 2023 · 2 min read

Index to reduce context limitations

There is a very simple, standardized way of solving the problem of too small GPT context windows. This is what to do when the context window gets full:

24 Mar 2023 · 2 min read