Noah Bilgrien (@nobillygreen) 's Twitter Profile
Noah Bilgrien

@nobillygreen

AI, creativity, intelligence augmentation. More interested in jetpacks than robots.

ID: 2205883771

calendar_today21-11-2013 00:24:59

239 Tweet

38 Followers

238 Following

👩‍💻 Paige Bailey (@dynamicwebpaige) 's Twitter Profile Photo

Two new websites that I'll be keeping handy for the foreseeable future: 🙌 tellina.rocks: translates natural language inputs into bash commands using TensorFlow 2.x 🐚 explainshell.com: beautiful, detailed manpage explanations for arbitrary shell commands

Two new websites that I'll be keeping handy for the foreseeable future:

🙌 tellina.rocks: translates natural language inputs into bash commands using <a href="/TensorFlow/">TensorFlow</a> 2.x

🐚 explainshell.com: beautiful, detailed manpage explanations for arbitrary shell commands
Noah Bilgrien (@nobillygreen) 's Twitter Profile Photo

Without a doubt the most insightful interview I've seen with Trump. Everyone should take the time to watch this youtu.be/zaaTZkqsaxY

Pete Skomoroch (@peteskomoroch) 's Twitter Profile Photo

ML people: Do you have a tool in your current model training workflow that is a secret weapon? Maybe something that labels data automatically, autotunes hyper-parameters, simplifies testing or does feature extraction? Tell us your secrets :)

Hugging Face (@huggingface) 's Twitter Profile Photo

Our API now includes a brand new pipeline: zero-shot text classification This feature lets you classify sequences into the specified class names out-of-the-box w/o any additional training in a few lines of code! 🚀 Try it out (and share screenshots 📷): huggingface.co/facebook/bart-…

Our API now includes a brand new pipeline: zero-shot text classification

This feature lets you classify sequences into the specified class names out-of-the-box w/o any additional training in a few lines of code! 🚀

Try it out (and share screenshots 📷): huggingface.co/facebook/bart-…
Graham Neubig (@gneubig) 's Twitter Profile Photo

Powerful LMs such as GPT-3 and T5 have impressive ability to answer questions by continuing a textual prompt. However, how can we know when an LM knows the answer with confidence, and when it's making a random guess? Our new preprint asks this: phontron.com/paper/jiang20l… 1/N

Powerful LMs such as GPT-3 and T5 have impressive ability to answer questions by continuing a textual prompt. However, how can we know when an LM knows the answer with confidence, and when it's making a random guess? Our new preprint asks this: phontron.com/paper/jiang20l… 1/N
Carlos Outeiral (@c_outeiral) 's Twitter Profile Photo

Interested in AlphaFold 2? Read my piece on how good it actually is, how it works, and what it means for the scientific community and those of us working in computational biology: blopig.com/blog/2020/12/c…

Corey Quinn (@quinnypig) 's Twitter Profile Photo

So there's a lot of confusion about what Parler being kicked off of Amazon Web Services (Amazon Web Services) means. Let me do a quick thread to explain it to folks who aren't deep in the technical weeds...

Matplotlib (@matplotlib) 's Twitter Profile Photo

We have this awesome function called sublots_mosaic where you can pass us a layout id'ed on name axd = plt.subplot_mosaic( """ ABD CCD """) matplotlib.org/stable/tutoria…

We have this awesome function called sublots_mosaic where you can pass us a layout id'ed on name 
axd = plt.subplot_mosaic(
    """
    ABD
    CCD
    """) 

matplotlib.org/stable/tutoria…
𝙷𝚒𝚖𝚊 𝙻𝚊𝚔𝚔𝚊𝚛𝚊𝚓𝚞 (@hima_lakkaraju) 's Twitter Profile Photo

If you have less than 3 hours to spare & want to learn (almost) everything about state-of-the-art explainable ML, this thread is for you! Below, I am sharing info about 4 of our recent tutorials on explainability presented at NeurIPS, AAAI, FAccT, and CHIL conferences. [1/n]

@terrymorse@mastodon.sdf.org🌎 (@terrymorse) 's Twitter Profile Photo

What are the one-year risks of COVID-19 for the general population? Possible outcomes are: – didn't catch it – infected, fully recovered – infected, long COVID – infected, death Here's a simple risk analysis for vaccinated and unvaccinated, based on published data.

What are the one-year risks of COVID-19 for the general population?

Possible outcomes are:
– didn't catch it
– infected, fully recovered
– infected, long COVID
– infected, death

Here's a simple risk analysis for vaccinated and unvaccinated, based on published data.
Chris McComb (he/him) (@ccmccomb) 's Twitter Profile Photo

This semester I've been teaching a new class on designing AI/ML products in MechSense, and as part of that class I have learned SO MUCH about great tools for ML rapid prototyping. Here are a few of my favorites:

Replicate (@replicate) 's Twitter Profile Photo

The Stable Diffusion innovation just doesn't stop! Here's a new open-source model from the MONA that produces seamless tiling images: replicate.com/tommoore515/ma…

The Stable Diffusion innovation just doesn't stop!

Here's a new open-source model from the <a href="/monaverse/">MONA</a> that produces seamless tiling images: replicate.com/tommoore515/ma…
Andrew Ng (@andrewyng) 's Twitter Profile Photo

Planning is a key agentic AI design pattern in which we use a large language model (LLM) to autonomously decide on what sequence of steps to execute to accomplish a larger task. For example, if we ask an agent to do online research on a given topic, we might use an LLM to break

fabian (@fabianstelzer) 's Twitter Profile Photo

introducing: ComfyAGI 🧙‍♂️😉 we've taught Claude to generate ComfyUI workflows, so you can now build comfy workflows just with prompts... We're open sourcing the entire prompt chain for this (which is a glif too), so u can remix & adapt it join our Discord & come hack with us: