iiinova — where your digital self keeps evolving

Smerity @smerity.bsky.social · 12/09/2025

Brainstorming with an LLM that's glazing you a tad is helpful when you're under glazing by default 🤔

Reposted by Smerity

Microplastics Sommelier @leastactionhero.bsky.social · 27/06/2024

einstein sent this to curie in 1911 when she was being harassed by tabloids. it contains everything you’d want in such a letter: (1) your haters are trash (2) you’re a baller, a true queen (3) i have determined the statistical law of motion of the diatomic molecule in planck’s radiation field 🧪⚛️

Prague, 23 November 1911
Highly esteemed Mrs. Curie,
Do not laugh at me for writing you without having anything sensible to say.
But I am so enraged by the base manner in which the public is presently daring to concern itself with you!? that I absolutely must give vent to this feeling. However, I am convinced that you consistently despise this rabble, whether it obsequiously lavishes respect on you or whether it attempts to satiate its lust for sensationalism!
I am impelled to tell you how much I have come to admire your intellect, your drive, and your honesty, and that I consider myself lucky to have made your personal acquaintance in Brussels. Anyone who does not number among these reptiles is certainly happy, now as before, that we have such personages among us as you, and Langevin(3) too, real people with whom one feels privileged to be in contact. If the rabble continues to occupy itself with you, then simply don't read that hogwash, but rather leave it to the reptile for whom i

6790203195

Reposted by Smerity

antirez @antirez.bsky.social · 04/01/2025

Very few people see a full video on YouTube apparently, even if it lasts just 10-15 minutes.

3417819

Smerity @smerity.bsky.social · 03/12/2024

My contribution to a discussion at hiddenstates.org on explorables/user interfaces for controlling ML tools > We're trying to rig soundboards to control LLMs thinking there's a well defined interface underneath when it's actually a button that drops fertilizer into the river of a complex ecosystem.

0100

Reposted by Smerity

Smerity @smerity.bsky.social · 29/11/2024

The fact that most wouldn't pay money for passive consumption "there" (reels, feed, ...) but do actively pay with the tick tock of our mind (hours spent, enriching the content locally, ...) is fascinating. If this is psychological obliteration we're very much an active participant in it.

041

Reposted by Smerity

Michael Nielsen @michaelnielsen.bsky.social · 29/11/2024

A new-to-me perspective on passive consumption of media (Also: I'm gifting you some psychological obliteration here!)

5434

Reposted by Smerity

kyunghyuncho.bsky.social @kyunghyuncho.bsky.social · 27/11/2024

congratulations, @ian-goodfellow.bsky.social, for the test-of-time award at @neuripsconf.bsky.social! this award reminds me of how GAN started with this one email ian sent to the Mila (then Lisa) lab mailing list in May 2014. super insightful and amazing execution!

318727

Smerity @smerity.bsky.social · 26/11/2024

Who is playing around with Bluesky at an API / data level? I've used the API to {read a bot's DMs, collect your likes, analyze your following / followers} (with heavy `time.sleep` for latter as I've not found bulk queries). Leaping into "Bluesky as a dataset" by exploring Jetstream. Hints?

1356

Smerity @smerity.bsky.social · 22/11/2024

Writing more Rust recently led me to a revelation about Python. Rust was vital to my original task, but only a few simplifications away, the shorter Python version leapt to almost as fast. I'd stumbled from a cold path to a hot path, part of a vast network of optimized trails in Python's ecosystem.

state.smerity.com

Smerity.com: Python isn't just glue, it's an implicit JIT ecosystem

The ecosystem wears in the desire paths, and when slow Python becomes a problem, the ecosystem doesn't optimize the Python, it paves new roads beneath

1467

Smerity @smerity.bsky.social · 20/11/2024

PSA: Are your Bluesky notifications a tad too loud? You can set Bluesky to only replies and quotes. Go to the Notifications tab (web or mobile) and click on the ⚙️ in the top right. Note: This option is not found under Settings

Notification Settings

Notification filters

Enable priority notifications [Toggle box]

Experimental: When this preference is enabled, you'll only receive reply and quote notifications from users you follow. We'll continue to add more controls here over time.

2179

Smerity @smerity.bsky.social · 20/11/2024

I still had muscle memory of typing "tw + Enter" to go to X, even a year and a half after the rename. Browser extensions exist redirecting Twitter / X to Bluesky but those were too extreme - I wrote one that _just_ redirects twitter.com to bsky.com so I could take advantage of that muscle memory 🤣

0200

Smerity @smerity.bsky.social · 19/11/2024

I'm wondering what the world would look like if there was a 🔴Big Red Button🔴 on each page of the documentation for {libraries, APIs, books, ...}. It doesn't even need to be complex. A heat map of pain is by itself such a strong signal given we lack insight even as simple as churn rate for non-use.

050

Reposted by Smerity

Christian S. Perone @cperone.bsky.social · 19/11/2024

Hi, just sharing an updated version of the PyTorch 2 Internals slides: drive.google.com/file/d/18YZV.... Content: basics, jit, dynamo, Inductor, export path and executorch. This is focused on internals so you will need a bit of C/C++. I show how you can export and run a model on a Pixel Watch too.

28617

Reposted by Smerity

Sebastian Loeschcke @sloeschcke.bsky.social · 18/11/2024

Ever wanted to train your own 13B Llama2 model from scratch on a 24GB GPU? Or fine-tune one without compromising performance compared to full training? 🦙 You now can, with LoQT: Low-Rank Adapters for Quantized Pretaining! arxiv.org/abs/2405.16528 1/4

23111

Reposted by Smerity

Jascha Sohl-Dickstein @jascha.sohldickstein.com · 12/02/2024

Have you ever done a dense grid search over neural network hyperparameters? Like a *really dense* grid search? It looks like this (!!). Blueish colors correspond to hyperparameters for which training converges, redish to those for which training diverges. Even better, a video: vimeo.com/903855670

$Examples of fractals resulting from neural network training in a variety of experimental configurations$

714031

Smerity @smerity.bsky.social · 19/11/2024

I love that Bluesky has App Passwords. Even better that Sky Follower Bridge, likely one of the first apps a new user will log in to, explicitly nudges you towards using an app password. There are still full blown APIs (and platforms / banks -_-) that don't allow per-app keys/passwords 😱

github.com

0101

Reposted by Smerity

Fabien Sanglard @fabinou.bsky.social · 17/11/2024

Game Engine Black Book: DOOM v1.2 Game Engine Black Book: WOLFENSTEIN 3D v2.2 The Book of CP-System v1.0 Free pdfs, high-quality 80g premium color prints, PlayStore, and source code are now available. fabiensanglard.net/three_books_...

59923

Smerity @smerity.bsky.social · 19/11/2024

If we were mutuals on Twitter ping me and I'll follow you here :) I found ~800 of the 2.5k follows I have on Twitter / X, a starting point! Auto-migration had false positives but the feed's core (ML / computing) and flavour (art, science, graphics, ...) transferred ^_^ www.sky-follower-bridge.dev

sky-follower-bridge.dev

Sky Follower Bridge

Instantly find and follow the same users from your 𝕏 followers on Bluesky

2180

Reposted by Smerity

Kayo Yin @kayoyin.bsky.social · 19/11/2024

🚨New dataset + challenge🚨 We release ASL STEM Wiki: the first signing dataset of STEM articles! 📰 254 Wikipedia articles 📹 ~300 hours of ASL interpretations 👋 New task: automatic sign suggestion to make STEM education more accessible microsoft.com/en-us/resear... 🧵 #EMNLP2024

23710

Smerity @smerity.bsky.social · 19/11/2024

PSA: By default, only people you follow can send you DMs. If you want your profile to be open to serendipitous DMs from new possible friends it's an explicit option you need to select :)

Chat Settings > Allow New Messages from > Everyone / Users I Follow / No one

0163

Reposted by Smerity

Neil Traft @ntraft.bsky.social · 18/11/2024

On how Bluesky starter packs might flatten the typical rich-get-richer power law dynamics of social media connections... For a time, at least... Gotta love a good complexity science meta-post!

061

Reposted by Smerity

Maike Osborne @maosbot.bsky.social · 09/11/2024

New here? Interested in AI/ML? Check out these great starter packs! AI: go.bsky.app/SipA7it RL: go.bsky.app/3WPHcHg Women in AI: go.bsky.app/LaGDpqg NLP: go.bsky.app/SngwGeS AI and news: go.bsky.app/5sFqVNS You can also search all starter packs here: blueskydirectory.com/starter-pack...

66557212

Reposted by Smerity

David Gasquez @davidgasquez.com · 14/11/2024

New post up! ✨ Exploring AT Protocol with Python to visualize the #databs social graph! davidgasquez.com/exploring-at... Took less than 1 hour to get the data and plot it. Amazing what you can do with open APIs and great SDKs!

1210820

Reposted by Smerity

JD Long @jdlong.cerebralmastication.com · 16/11/2024

This Bluesky follow finder is super neat. It finds folks you don’t follow who follow folks you follow. So it helps fill in your network. It’s the type of cool stuff enabled by an open ecosystem. bsky-follow-finder.theo.io

bsky-follow-finder.theo.io

Bluesky Network Analyzer

Find accounts that you don't follow (yet) but are followed by lots of accounts that you do follow.

1915452

Smerity @smerity.bsky.social · 16/11/2024

My joke paper that uses the non-linear non-sensical pricing of chicken nuggets in fast food to power a novel activation function for ML models had: (a) A citation (b) For a definition I'm proud of and want better known (c) In a paper + thesis about using ML for typhoon satellite imagery Happy days!

Dropout
Another powerful regularisation technique is dropout [52], which consists of randomly setting some activations to zero. It aims to prevent specific units (neurons) to co-adapt too much. A very concise yet simple definition of dropout has been recently given by [53]:

[...]. Dropout, simply described, is the concept that if you can
learn how to do a task repeatedly whilst drunk, you should be
able to do the task even better when sober. [...]

0120

Smerity @smerity.bsky.social · 16/11/2024

At least Gemini Advanced and I are in agreement that losing unrelated features when you set "Gemini Apps Activity" to off in order to prevent Google training on your conversations (even as a paying customer) is a dark pattern 🤔

Smerity asks Gemini Advanced: "Is there any option to use Gemini without having my data used by Google for training? Losing all history in the Gemini interface seems like a purposeful design decision to take away features from users who don't want their data used."

Gemini Advanced answers: "You're right to be concerned about this. It does seem like a design decision to encourage data sharing. Unfortunately, there's no way to completely prevent Google from using your data when using Gemini, even with Gemini Advanced."

150