Josh Albrecht
8 statements across 1 episodes · 2 bullish · 2 bearish · 1 people on the record · first statement Jun 25, 2024 by Josh Albrecht · said 8 times in 1 episodes since 2023 · across every show →
On the record as a speaker too: Josh Albrecht's record, appearances and statements → this page counts the times other people say the name.
Mentions by year
brought up most by Kanjun Qiu (8)
tap a year for its mentions
2023 8 mentions in 1 episode
Everything said about Josh Albrecht, oldest first
Jun 25, 2024 negative
Albrecht: Optimizing for competitive coding benchmarks does not create useful programmers
“Like, we do a lot of code generation, but we don't really do a lot on, like, code competition problems for the very, very hard ones, so that you can go very far down that route and make something like really good at those problems, but not actually that useful…”
Jun 25, 2024 negative
Albrecht: AgentBench paper's appendix examples are actually incorrect solutions
“Like we were looking at the agent bench paper, I think just last week for our paper club. And one of the things that we noticed is that actually like both of the examples in the appendix that are given as like traces where it got it right. This is actually not…”
Jun 25, 2024
Albrecht: Imbue Manages Infrastructure with Three to Six Engineers
“Like our infrastructure team is like
You know, it fluctuates from week to week, depending on like how many things are on fire and how much we need to build.
But it's like between like three and six people, like it's small.
It's not like some huge team of like …”
Jun 25, 2024
Albrecht: 4K GPU clusters require 3-tier networking versus standard 1K 2-tier setups
“The normal, the like vanilla setup or, you know, these large clusters as vanilla as it can be is what's normally like a 127 node cluster. So closer to like 10, 24 GPUs instead of 4000. Here we have a larger cluster. As you start to get into the larger clusters…”
Jun 25, 2024 neutral
Jun 25, 2024 positive
Albrecht: Coding agents communicating uncertainty are far more useful than slightly more accurate ones
“I would much rather have a coding agent that will give me back a thing. And you know, it's actually the code doesn't work like 10% less of the time than some other model, but it will tell me a hundred percent of the time. When it got like when it's not sure, l…”
Jun 25, 2024
Jun 25, 2024 bullish
Albrecht: Code execution expands agent capabilities far beyond hard-coded tool calling
“Instead of worrying about like weird hard coded agents using tools, Like let's just make them able to actually write code robustly and make that code work and be able to debug that code, know if that code is safe to run, like get really good at the like code w…”