Tim Sweeney 🧢

@mattshumer_ uses expensive LLMs to "teach" smaller LLMs to perform well on a given task. @wandb's Weave (wandb.github.io/weave/) pairs well 🍷: code tracking, execution tracing, model versioning/sharing, dataset management, and evaluations! youtube.com/watch?v=mkUpb9…

@mattshumer_ @wandb youtube.com/watch?v=mkUpb9…

@mattshumer_ uses expensive LLMs to "teach" smaller LLMs to perform well on a given task. @wandb's Weave (wandb.github.io/weave/) pairs well 🍷: code tracking, execution tracing, model versioning/sharing, dataset management, and evaluations! youtube.com/watch?v=mkUpb9…

@mattshumer_ Wonderful idea @mattshumer_ ! I think @wandb's Weave (wandb.github.io/weave/) could complement this work nicely (: I made a video showcasing some possible benefits: x.com/timssweeney/st…

Introducing `llama-405b-to-8b` ✍️ Get the quality of Llama 3.1 405B, at a fraction of the cost and latency. Give one example of your task, and 405B will teach 8B (~30x cheaper!!) how to do the task perfectly. And it's open-source: github.com/mshumer/gpt-pr…

🧵 Weave team is cranking! New eval comparison UI just landed. Get a beautiful high level summary of how your evals stack up, and then drill down to look at actual data in areas of disagreement. This is a beta feature you can use now. We’d love feedback.

I'm very excited to announce Weave, our new tools to track and evaluate your LLM apps. Use Weave to: 🍩log and version LLM interactions and surrounding data, from development to production 🍩experiment with prompting techniques, model changes, and parameters 🍩evaluate your models and measure your progress

@anthony_bak @BEBischof @wandb @leland_mcinnes Given a Table, the projector will automatically select either the first column which is list<number>, or if none exists, will autoselect all number columns. Here is an example where we have an image column (which is mapped to the overlay): wandb.ai/timssweeney/em…

@BEBischof @wandb @leland_mcinnes What do you do with mixed type tables? Like, numbers and categories and text all in one table.

So you wanna log your rich data to Tables and have a quick UI integration to apply Dimension Reduction and Projection? We gotchu: Check out @wandb' new Dimension Projector! I'm super excited about this feature. :D

@KarlMorin_ Is this a public dashboard?

Who broke this internet this time arround? GCP?

@tylerbeaty_ Nice work @tylerbeaty_ ! Looks sleek and clean - can't wait to try it myself (: I admire your dedication to helping people help become better versions of themselves - keep it up!

We’ve been hard at work building Tables, a new way to organize, understand and improve your data. Today we're opening it up to everyone! Try it here: wandb.ai/wandb/posts/re…

@nicolasdnl Very impressive illusion - I love it. What are you using to create this?

Surprise Remake

@nimalan The irony (see who is below you in my feed):

This happens on EVERY SINGLE app open, even when I kill the app and reopen it, and seems a little questionable to me.

.@YouTube why do I keep seeing Trump ads at the very top of my screen upon opening your app, and why is there no way to opt out of them? And what's up with this racist/sexist garbage ad in particular? I don't want to see this 💩 and should be able to opt out.

@streamlit Awesome work! Can't wait to try it out (:

The new layout options inspired the team to #rock out in #python 😎🎸 🧑‍🎤 volume up for full enjoyment pip install --upgrade streamlit 🤘 read more: blog.streamlit.io/introducing-ne…

One of the most impressive and certainly applicable uses of NNs I have seen in a long while. Fantastic work!

When talking to people who haven’t deployed ML models, I keep hearing a lot of misperceptions about ML models in production. Here are a few of them. (1/6)

@ankurparikh @fermatslibrary This is exactly what I did was well. I was surprised how many other approaches there were!

@fermatslibrary Re-write the numerator as: (10+0)^2 + (10+1)^2 + (10+2)^2 + (10+3)^2 + (10+4)^2 Expand each term using (a+b)^2 = a^2 + 2ab + b^2 (a^2) terms sum to: 500 (2*a*b) terms: 0 + 20 + 40 + 60 + 80 = 200 (b^2) terms: 0 + 1 + 4 + 9 + 16 = 30 500+200+30 = 730 730/365 = 2

In 1895, Nikolay Bogdanov-Belsky painted the famous: "Mental Arithmetic. In the Public School of S. Rachinsky." The problem on the blackboard is (10²+11²+12²+13²+14²)/365, can you find a way to solve it with mental arithmetic?

@kovasb @stephen_wolfram So cool!!

Got a signed copy of @stephen_wolfram 's latest. So jealous of the the current team! Really excited on progress so far & can't wait to apply some graph deep learning to study these systems.

@streamlit Awesome work! Giving the community the chance to build components allows us to solve our own problems, and builds up the Streamlit offering way faster than a single team can! Fantastic! (:

We're excited to announce our new Streamlit Components API - releasing the new superpower of using and creating community driven elements and widgets 🤩 📰 Read more: medium.com/streamlit/intr… 🎈 Upgrade to 0.63.0 to test out pip install --upgrade streamlit #DataViz #OpenSource

WOW!!! #SanDiego #BlackLivesMatter

@AlecStapp I am pretty sure @profgalloway's headline quote was from his podcast. Specifically the the 18:14 mark of "Get To a Platform" open.spotify.com/episode/5Arf9D…. He is using a grand statement to elicit the interviewee to also make a strong claim. (although possible he said to wsj as well)

This explains so much

@jasonfried - collaborative authoring - deep linking to email for easy reference - tree-based visualization. (replies, reply-all, forwards, change of recipients)... All creates a mess linearly. - simple, yet appropriately powerful rich text editor - any method of helping clear/avoid junk

Let’s show off some more HEY today. Anything you *imagine* you’d like to see?