Remy Guercio
@remy.guerc.io
Planes, trains, and occasionally automobiles.
PMM @tailscale.com,📍 NOLA
PMM @tailscale.com,📍 NOLA
Hah @chrisckchang.bsky.social the trend is Accidental ASMR not ASMR. Regardless of if it’s accidental or not.
January 6, 2025 at 6:35 PM
Hah @chrisckchang.bsky.social the trend is Accidental ASMR not ASMR. Regardless of if it’s accidental or not.
Analytics + session recording + surveys means you can do things like search for users who did X & Y, gave some answer, and then watch what actually happened.
I agree about talking to folks, but it’s a helpful complement.
I agree about talking to folks, but it’s a helpful complement.
January 6, 2025 at 7:09 AM
Analytics + session recording + surveys means you can do things like search for users who did X & Y, gave some answer, and then watch what actually happened.
I agree about talking to folks, but it’s a helpful complement.
I agree about talking to folks, but it’s a helpful complement.
That almost sounds Facebook inflated video views level of suspicious.
January 6, 2025 at 1:59 AM
That almost sounds Facebook inflated video views level of suspicious.
It’s my favorite piece of B2B SaaS that I’ve used in a while.
Posthog is up there on that list for me too. If you get it set up right, it’s essentially Gong but for PLG / self-serve rather than sales.
Posthog is up there on that list for me too. If you get it set up right, it’s essentially Gong but for PLG / self-serve rather than sales.
January 6, 2025 at 1:36 AM
It’s my favorite piece of B2B SaaS that I’ve used in a while.
Posthog is up there on that list for me too. If you get it set up right, it’s essentially Gong but for PLG / self-serve rather than sales.
Posthog is up there on that list for me too. If you get it set up right, it’s essentially Gong but for PLG / self-serve rather than sales.
The related work section of this paper from last year is quite useful. Prediction vs compression, effects of tokenization, etc…
arxiv.org/pdf/2309.10668
arxiv.org/pdf/2309.10668
arxiv.org
December 30, 2024 at 8:03 PM
The related work section of this paper from last year is quite useful. Prediction vs compression, effects of tokenization, etc…
arxiv.org/pdf/2309.10668
arxiv.org/pdf/2309.10668
Overfit is almost desired in this instance.
December 30, 2024 at 2:57 PM
Overfit is almost desired in this instance.
Yeah I guess the better it is at predicting the next token the tighter the encoding.
In this world it seems like you might want a ton of small LLMs with really tight training sets for a given context.
Things always get very odd to me when you need to use a model at temperature 0.
In this world it seems like you might want a ton of small LLMs with really tight training sets for a given context.
Things always get very odd to me when you need to use a model at temperature 0.
December 30, 2024 at 2:55 PM
Yeah I guess the better it is at predicting the next token the tighter the encoding.
In this world it seems like you might want a ton of small LLMs with really tight training sets for a given context.
Things always get very odd to me when you need to use a model at temperature 0.
In this world it seems like you might want a ton of small LLMs with really tight training sets for a given context.
Things always get very odd to me when you need to use a model at temperature 0.
Or is this the embedding vector represented as characters?
LLMs and compression are Interesting nonetheless. Still a little bit of a head scratcher.
LLMs and compression are Interesting nonetheless. Still a little bit of a head scratcher.
December 30, 2024 at 2:34 PM
Or is this the embedding vector represented as characters?
LLMs and compression are Interesting nonetheless. Still a little bit of a head scratcher.
LLMs and compression are Interesting nonetheless. Still a little bit of a head scratcher.
Wouldn’t you expect better compression with what is effectively a pre-shared dictionary of ~170MB?
They say the training text is mostly English and code, so it seems like either there are still a bunch of Chinese characters being used as high context tokens or something happened with the tokenizer?
They say the training text is mostly English and code, so it seems like either there are still a bunch of Chinese characters being used as high context tokens or something happened with the tokenizer?
December 30, 2024 at 2:24 PM
Wouldn’t you expect better compression with what is effectively a pre-shared dictionary of ~170MB?
They say the training text is mostly English and code, so it seems like either there are still a bunch of Chinese characters being used as high context tokens or something happened with the tokenizer?
They say the training text is mostly English and code, so it seems like either there are still a bunch of Chinese characters being used as high context tokens or something happened with the tokenizer?
AMD can come close on “raw” numbers, but in the real world you’re getting only a fraction.
December 25, 2024 at 7:19 PM
AMD can come close on “raw” numbers, but in the real world you’re getting only a fraction.
I’m not sure how’d you’d even reasonably do the compute comparison per $ over more than a few years. It’s hard enough as it is to compare real world FP16, INT8, etc… perf.
Lambda does its best for NVIDIA GPUs, but you have to look at specific models / precisions.
lambdalabs.com/gpu-benchmarks
Lambda does its best for NVIDIA GPUs, but you have to look at specific models / precisions.
lambdalabs.com/gpu-benchmarks
GPU Benchmarks for Deep Learning | Lambda
Lambda’s GPU benchmarks for deep learning are run on over a dozen different GPU types in multiple configurations. GPU performance is measured running models for computer vision (CV), natural language ...
lambdalabs.com
December 25, 2024 at 7:17 PM
I’m not sure how’d you’d even reasonably do the compute comparison per $ over more than a few years. It’s hard enough as it is to compare real world FP16, INT8, etc… perf.
Lambda does its best for NVIDIA GPUs, but you have to look at specific models / precisions.
lambdalabs.com/gpu-benchmarks
Lambda does its best for NVIDIA GPUs, but you have to look at specific models / precisions.
lambdalabs.com/gpu-benchmarks
Backblaze has the most comprehensive spinning disk numbers I’ve seen. Haven’t found the same for SSD (SATA, NVMe, or otherwise).
www.backblaze.com/blog/hard-dr...
www.backblaze.com/blog/hard-dr...
December 25, 2024 at 7:09 PM
Backblaze has the most comprehensive spinning disk numbers I’ve seen. Haven’t found the same for SSD (SATA, NVMe, or otherwise).
www.backblaze.com/blog/hard-dr...
www.backblaze.com/blog/hard-dr...
The Tet from Oblivion would like to have a word with you.
December 17, 2024 at 8:09 AM
The Tet from Oblivion would like to have a word with you.
Hah not sure I wanted to know that I’m at 16.5 with 6 more flights to go…
December 9, 2024 at 6:00 PM
Hah not sure I wanted to know that I’m at 16.5 with 6 more flights to go…
Hah this feels like it’s part of the creative brief for some high fashion men’s workwear line.
December 7, 2024 at 9:53 PM
Hah this feels like it’s part of the creative brief for some high fashion men’s workwear line.