Denis Shepelin
@denshe.bsky.social
Formerly Comp Biotech PhD @ NNF Center for Biosustainability DTU.
Now ML at LabForward, digital tools for Labs.
Berlin, Germany
Now ML at LabForward, digital tools for Labs.
Berlin, Germany
Great summary! Uv indeed feels very magical and as there was a team that polished that for like 15 years.
The time has come. The prophecy is accomplished.
We are going to review one year of uv usage to ponder the pros, the cons, and whether you should migrate.
It's a long article, but I have a 10 lines TL;DR at the top, you can pretend you read the whole thing :)
open.substack.com/pub/bitecode...
We are going to review one year of uv usage to ponder the pros, the cons, and whether you should migrate.
It's a long article, but I have a 10 lines TL;DR at the top, you can pretend you read the whole thing :)
open.substack.com/pub/bitecode...
A year of uv: pros, cons, and should you migrate
Yes, probably.
open.substack.com
February 15, 2025 at 9:54 PM
Great summary! Uv indeed feels very magical and as there was a team that polished that for like 15 years.
Reposted by Denis Shepelin
The time has come. The prophecy is accomplished.
We are going to review one year of uv usage to ponder the pros, the cons, and whether you should migrate.
It's a long article, but I have a 10 lines TL;DR at the top, you can pretend you read the whole thing :)
open.substack.com/pub/bitecode...
We are going to review one year of uv usage to ponder the pros, the cons, and whether you should migrate.
It's a long article, but I have a 10 lines TL;DR at the top, you can pretend you read the whole thing :)
open.substack.com/pub/bitecode...
A year of uv: pros, cons, and should you migrate
Yes, probably.
open.substack.com
February 15, 2025 at 12:56 PM
The time has come. The prophecy is accomplished.
We are going to review one year of uv usage to ponder the pros, the cons, and whether you should migrate.
It's a long article, but I have a 10 lines TL;DR at the top, you can pretend you read the whole thing :)
open.substack.com/pub/bitecode...
We are going to review one year of uv usage to ponder the pros, the cons, and whether you should migrate.
It's a long article, but I have a 10 lines TL;DR at the top, you can pretend you read the whole thing :)
open.substack.com/pub/bitecode...
Extremely weird to see supposedly rust-first project being a thin wrapper around Java based Apache Tika and C++ Tesseract. github.com/yobix-ai/ext...
We've done full circle
We've done full circle
GitHub - yobix-ai/extractous: Fast and efficient unstructured data extraction. Written in Rust with bindings for many languages.
Fast and efficient unstructured data extraction. Written in Rust with bindings for many languages. - yobix-ai/extractous
github.com
January 30, 2025 at 10:58 AM
Extremely weird to see supposedly rust-first project being a thin wrapper around Java based Apache Tika and C++ Tesseract. github.com/yobix-ai/ext...
We've done full circle
We've done full circle
This is great news huggingface.co/blog/modernb...
Not everything needs to be fed through LLM and for that we now have much better foundation for tons of apps that work with texts but not necessarily need to generate any, so classification, NER, similarity scores.
Not everything needs to be fed through LLM and for that we now have much better foundation for tons of apps that work with texts but not necessarily need to generate any, so classification, NER, similarity scores.
Finally, a Replacement for BERT: Introducing ModernBERT
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
huggingface.co
December 19, 2024 at 7:05 PM
This is great news huggingface.co/blog/modernb...
Not everything needs to be fed through LLM and for that we now have much better foundation for tons of apps that work with texts but not necessarily need to generate any, so classification, NER, similarity scores.
Not everything needs to be fed through LLM and for that we now have much better foundation for tons of apps that work with texts but not necessarily need to generate any, so classification, NER, similarity scores.
Reposted by Denis Shepelin
Learning about quantization suffixes while `ollama pull llama3.3` download completes (fyi, quantization for the default 70b is q4_K_M)
• make-ggml .py: github.com/ggerganov/ll...
• pull request: github.com/ggerganov/ll...
• make-ggml .py: github.com/ggerganov/ll...
• pull request: github.com/ggerganov/ll...
December 7, 2024 at 1:09 AM
Learning about quantization suffixes while `ollama pull llama3.3` download completes (fyi, quantization for the default 70b is q4_K_M)
• make-ggml .py: github.com/ggerganov/ll...
• pull request: github.com/ggerganov/ll...
• make-ggml .py: github.com/ggerganov/ll...
• pull request: github.com/ggerganov/ll...
aws.amazon.com/ai/generativ... Looks quite impressive. I really appreciate the direction towards cost and speed optimization rather than accuracy for most cases I care about.
Generative Foundation Model - Amazon Nova - AWS
Amazon Nova is a generation of state-of-the-art (SOTA) foundation model that delivers frontier intelligence and industry leading price-performance.
aws.amazon.com
December 3, 2024 at 8:11 PM
aws.amazon.com/ai/generativ... Looks quite impressive. I really appreciate the direction towards cost and speed optimization rather than accuracy for most cases I care about.
Structured outputs make no negative impact on reasoning abilities of LLMs (I've also observed that in practice).
Key takeaways:
1. Proper design of prompts is important
Even the most senior researchers can do wrong. Many builtin prompts in packages are also bad.
blog.dottxt.co/say-what-you...
Key takeaways:
1. Proper design of prompts is important
Even the most senior researchers can do wrong. Many builtin prompts in packages are also bad.
blog.dottxt.co/say-what-you...
Say What You Mean: A Response to 'Let Me Speak Freely'
blog.dottxt.co
November 25, 2024 at 12:24 PM
Structured outputs make no negative impact on reasoning abilities of LLMs (I've also observed that in practice).
Key takeaways:
1. Proper design of prompts is important
Even the most senior researchers can do wrong. Many builtin prompts in packages are also bad.
blog.dottxt.co/say-what-you...
Key takeaways:
1. Proper design of prompts is important
Even the most senior researchers can do wrong. Many builtin prompts in packages are also bad.
blog.dottxt.co/say-what-you...
Reposted by Denis Shepelin
Also: you can also use variables (or expressions?!) for the formatting information! #Python is cool...
More details and explanation at fstring.help
More details and explanation at fstring.help
November 21, 2024 at 5:50 PM
Also: you can also use variables (or expressions?!) for the formatting information! #Python is cool...
More details and explanation at fstring.help
More details and explanation at fstring.help
Maybe one can also interact with aging data as well.
Remind that there was something really interesting back then, but forgotten for a while in Read-It-Later style of apps for example. Or liberate the users like Arc browser does with their auto-discarded tabs.
Remind that there was something really interesting back then, but forgotten for a while in Read-It-Later style of apps for example. Or liberate the users like Arc browser does with their auto-discarded tabs.
As I'm yet again not finding my notion document but random other old things, I ask you to consider writing more software that intentionally decays and loses data. lucumr.pocoo.org/2024/10/30/m...
Make It Ephemeral: Software Should Decay and Lose Data
Make software that is capable to forget and decay information.
lucumr.pocoo.org
October 30, 2024 at 2:02 PM
Maybe one can also interact with aging data as well.
Remind that there was something really interesting back then, but forgotten for a while in Read-It-Later style of apps for example. Or liberate the users like Arc browser does with their auto-discarded tabs.
Remind that there was something really interesting back then, but forgotten for a while in Read-It-Later style of apps for example. Or liberate the users like Arc browser does with their auto-discarded tabs.
It's so strange to feel immediate ick on Twitter/X given their update that
1) made videos autoplay
2) pushed too many "meme"/tiktok/youtube shorts like entertainment videos
3) pushed me to Followed tab
to only find extremely low activity of people whom I actually following there.
1) made videos autoplay
2) pushed too many "meme"/tiktok/youtube shorts like entertainment videos
3) pushed me to Followed tab
to only find extremely low activity of people whom I actually following there.
October 27, 2024 at 8:28 PM
It's so strange to feel immediate ick on Twitter/X given their update that
1) made videos autoplay
2) pushed too many "meme"/tiktok/youtube shorts like entertainment videos
3) pushed me to Followed tab
to only find extremely low activity of people whom I actually following there.
1) made videos autoplay
2) pushed too many "meme"/tiktok/youtube shorts like entertainment videos
3) pushed me to Followed tab
to only find extremely low activity of people whom I actually following there.