Anatoly Tsyplenkov

Holding a PhD in hydrology, interested in riverine sediment transport issues and all things #geospatial. Love mountains, mystery stories and #rstats 🤎

[Anatoly Tsyplenkov @atsyplen]

Huge update to the {pastum} VS Code extension — you can now control the decimal separator (point or comma). Paste as default dataframe is now sensitive to the editor language, so you can easily paste in your favorite format with just one click. See some showcases below.

[Anatoly Tsyplenkov @atsyplen]

@Chris_T_Kenny Oh, I like the atlas! Very neat. What framework has you used? Was it. Observable?

[Mario Zechner @badlogicgames]

recommended viewing by @helloiamleonie !

[Zed @zeddotdev]

Terminal Threads are live in Zed v1.3.5!

You can now run claude, amp, pi, or any terminal-based workflow as a managed thread in the Threads Sidebar, right next to your other agent threads.

[Anatoly Tsyplenkov @atsyplen]

Omarchy is on the way...

Zed — https://t.co/aXNFSelLfU

Pi - https://t.co/6ZuqfcP8HT

[Anatoly Tsyplenkov @atsyplen]

I've been using non-VS Code based IDEs more and more lately. But I found that I became so used to the @system76 Pop Dark theme created by @ArtisanByteCrafter

So I have ported it for @zeddotdev and the Pi. I cannot help myself, I love these warm colours, especially in Zed.

[Anatoly Tsyplenkov @atsyplen]

@kennedymwavu What you have done... I have never heard of Omarchy and now I can't wait for the weekend to try it.

[Anatoly Tsyplenkov @atsyplen]

@lino_locurcio @EmmanuelIgunza @aiwithjainam Hmm, the shared link seems to be corrupted. Anyways, just check this table recognition. All I've done is uploaded the PDF paper to the https://t.co/oEZgFjcY5k

[Anatoly Tsyplenkov @atsyplen]

@lino_locurcio @EmmanuelIgunza @aiwithjainam Forget what I said. The GLM-OCR is much better and works in the web.

Check this out

https://t.co/xKMjYvV97f

[Anatoly Tsyplenkov @atsyplen]

@lino_locurcio @EmmanuelIgunza @aiwithjainam From my experience the way LLM converts PDF to md matters most. By default it probably uses very quick parsers, which can lead to information loss. Here is an example of using the marker lib to convert the Elseveir's paper. Left is quick, right is slow with postprocessing

[Anatoly Tsyplenkov @atsyplen]

God bless the limits reset

[Tibo @thsottiaux]

Yes

https://t.co/8Zx3k6xuK1

Whoever made this, you made me laugh.

[Anatoly Tsyplenkov @atsyplen]

5/5
I have designed it for Codex, but should work in any CLI agent

https://t.co/CF2YR9tjy6

[Anatoly Tsyplenkov @atsyplen]

I still write my own papers, but finding that one missing citation during major revisions is a massive flow-breaker.

To fix this, I'm proposing `scholar-labs-search` a #Codex/#Claude Code skill that uses Google Scholar Labs to find the best-fit papers for any topic. 🧵👇

[Anatoly Tsyplenkov @atsyplen]

4/5
Since this is a bit of a hack (relying on browser automation), I am really curious about how the rest of the community is solving this. How else are you getting your agents to handle literature searches? Are you relying on Semantic Scholar/OpenAlex APIs?

#academicchatter

[Ryzerth 🐲 @ryzerth]

Someone wants me to rename the Microkernel I wrote when I was a kid... Brother, I don't give a shit AIs see my decade old project more than your slop, you should have checked that before naming your shit. I'm not changing history because of your naming incompetence.

[Christopher T. Kenny, PhD @Chris_T_Kenny]

Here's a quick guide to setting up an LSP for R, since it's not supported by default in Anthropic's official plugins:

https://t.co/o69WWNDQyO

[Anatoly Tsyplenkov @atsyplen]

@Chris_T_Kenny Great intention!
FYI https://t.co/hhZlPn1jEX

[Anatoly Tsyplenkov @atsyplen]

@AJThurston I am using it and it works just fine! Try to delete the zotero-library-1.json and trigger regeneration

[Anatoly Tsyplenkov @atsyplen]

@luongnv89 @ollama @Kimi_Moonshot It works, indeed! But its v slow. I do have 2-3 t/s speed here in Spain