Marek Rogala

Co-founder of Appsilon.
Loves sailing and singing. ⛵️

[Marek Rogala @marekrog]

#GPT4 is way better at generating code than previous versions!

See a #rstats #shiny app fully generated by GPT-4. It displays a ggplot of mtcars, uses {shiny.semantic} for UI and has some nice styling in CSS 🚀

This level was impossible to achieve in GPT3.

Here's the process🧵

[Marek Rogala @marekrog]

Had a chance to talk to @zyla_kamil, who just released Rhino 1.9. I asked him what are the biggest updates in the recent releases.

Rhino revolutionizes building R Shiny apps for enterprise. Best programming practices, automates them in code, adds modularity, easier maintenance.

[Appsilon @appsilon]

Curious about #Rhino and its recent updates? Watch our video with Marek Rogala and Kamil Żyła as we break down Rhino 1.8 & 1.9 features, including box.linters integration, JS & Sass tools, and more! 🚀

Watch now: https://t.co/eDL3xVy9J8

#rpackage #rshiny #rstats #Rhinoverse

[Marek Rogala @marekrog]

@tylanmillertech hi! i came across MyToDoIst ChatGPT, are you the creator? I'm looking to use ChatGPT to interact with my Todoist, seems like this is exactly what you built? I'm looking to find out if this is being maintained; the link to github doesn't show any related repo

[Marek Rogala @marekrog]

@dickiebush review

[elvis @omarsar0]

Another huge release on the long-context LLMs front:

Introducing Giraffe 70B, an open-source LLM fine-tuned from base Llama 2 with context length extended to 32K.

The @abacusai team conducted an evaluation of the model assessing performance over long contexts.

The 70B model improves significantly at the longest context windows (32k) for the document QA task vs. the 13B model, scoring 61% accuracy vs. the 18% accuracy of 13B on the AltQA dataset.

I got excited with the earlier release of Giraffe because of the potential of these long context models to unlock unique applications.

Even more exciting to see that the 70B Giraffe model shows the best performance of all the open-source models in key categories like extraction, coding, and math.

Note that there is still a gap in performance to the best closed source models like GPT-4 but it's coming closer.

I also wonder how these models could help with key capabilities like information extraction, large-form doc analysis, and reasoning. There is a lot to explore with these long-context models. Don't sleep on these. Great work by the Abacus team.

Blog: https://t.co/GKemXoIS3O
Model: https://t.co/CY6Ji3fYpO

[Paweł Przytuła @pawel_appsilon]

This is huge! @jcheng announced Shinylive for R at #positconf2023 🔥

Now you can:

1. Convert Shiny to static HTML/CSS/JS/wasm
2. Write Shiny apps directly in a browser
3. Embed Shiny as Quarto code chunks in other webapps

#rshiny #rstats #positconf

[Marek Rogala @marekrog]

@Armosid did an in-depth overview of Shiny applications in Pharma and Biotech area 👀

[Ismael Rodríguez @Armosid]

💡Here is a list of really cool Shiny apps for Pharma and Biotech:
https://t.co/lemt2Einkg

We've recently launched these two:
FDA-Pilot-App: https://t.co/0MSqh9QlKN
Drug Interactions App: https://t.co/r241K23D2l

📩Contact us to collaborate on 🤖Machine Learning🤖 projects!

[Ismael Rodríguez @Armosid]

💡Here is a list of really cool Shiny apps for Pharma and Biotech:
https://t.co/lemt2Einkg

We've recently launched these two:
FDA-Pilot-App: https://t.co/0MSqh9QlKN
Drug Interactions App: https://t.co/r241K23D2l

📩Contact us to collaborate on 🤖Machine Learning🤖 projects!

[Jakub Nowicki @q_nowicki]

Who says @posit_pbc Connect is just for #RStats 📊 and #Python 🐍?

Our team has paved the way for #Rust 🦀 #Actix APIs.

Learn more: https://t.co/ohHk8dSNlg

🚀 #TechInnovation

[Jakub Nowicki @q_nowicki]

🚀 Guess what? 🚀
{shiny.emptystate} has just landed on CRAN! 🎊

Meet a new member of #Rhinoverse and learn how to easily manage situations when there is nothing (yet) to show in your #RShiny application.

Check the documentation to learn more: https://t.co/kpEHw9RylX

#RStats

[Jakub Nowicki @q_nowicki]

Optimizing #RShiny applications with webR is a game-changer 🤯 By leveraging browser-based computation, we witness a significant reduction in server load and enhanced responsiveness.

Dive deeper into the technical insights: https://t.co/lddm0Qc7mn

#webR #RStats

[Ismael Rodríguez @Armosid]

🧬 We've successfully adapted the R Submissions Pilot 2 Shiny App submitted to the FDA to our latest framework - #Rhino

📊 Our open-source app (FDA pilot app) provides a groundbreaking example of an R/Shiny app that can be submitted to the FDA.

📖 https://t.co/RkozljXqWo

#FDA

[Jakub Nowicki @q_nowicki]

Looking for tools to move your #RShiny application to the next level?

Check out the #Rhinoverse - a family of #RStats packages built around {rhino}: https://t.co/R4c6zZcN45

[Marek Rogala @marekrog]

@ehalm_ Very interesting, would love to experiment with it!

[Marek Rogala @marekrog]

{data.validator} package lets you automate validation of the data your app relies on... and creates great-looking reports (in just a few lines of code!)

We've just released a new version with a number of updates. #Rstats #Rshiny

[Jakub Nowicki @q_nowicki]

🎉{data.validator} 0.2.0 is on CRAN🎉

Validate your data and create great-looking reports with just a few lines of code!

Check out more: https://t.co/secrYB9Mu5

#RStats

[Marek Rogala @marekrog]

🎉 Big news! Our #Data4Good project, Mbaza, made it to the Top 10 Outstanding AI Projects by @ircai_unesco!
It helps preserve animals in national parks in Africa.

Catch our Head of AI, Jędrzej's live presentation in just a few mins: https://t.co/MXkpUUqp7E #SDG #Mbaza @appsilon

[Marek Rogala @marekrog]

@dickiebush 🤖🤖🤖

[Daniel Gross @danielgross]

Uses all the popular accoutrements such as LLaMA, LoRA, Langchain, etc.

[Marek Rogala @marekrog]

@Claybight @CanumaGdt Where?

[Haijun Xia @HaijunXia]

Stop reading the text !!! Have a graphic dialogue with OpenAI’s #GPT4 with #Graphologue. It turns GPT4-generated text into interactive node-link diagrams in real-time. New Human-Computer Interaction #HCI research makes #AI easier to use. More at https://t.co/2M90KhqNar

[Nicolae Rusan @NicolaeRusan]

What if AI agents could write their own tools/plugins?

Introducing 🧰 Toolkit: the easiest way to create & discover AI Plugins for 🦜📎LangChain and ChatGPT https://t.co/g3froFtxJu

Just describe a plugin in natural language, and get working LangChain Code. ChatGPT coming soon!