Alan Fregtman

Developer working in Immersive Entertainment by day. Comedian by night. Former Rigging TD.

Present: Developer @ @felixandpaul. ~ My opinions are my own.

[Alan Fregtman @alanwritescode]

"We don't make [weightpainting] mistakes.
We just have happy accidents." ♥
— #BobRoss, "The Joy of (Weight) Painting"

#rigtip Remember to be chill like Bob Ross, and just keep on painting until your deformations look right. It just takes time. ;)

#rigging #cgimemes

[Sadao Tokuyama @tokufxug]

画像と3Dデータの共通する位置を特定するAI「UniCorrn」が登場。

従来はデータの種類ごとに別のAIが必要でしたが、一つの仕組みで処理を統一。

その結果、従来手法を8%〜10%上回る精度で、写真と立体データ間の正確な位置合わせを可能にするAI技術です。

[tetsuo @tetsuoai]

Neural Network Visualization

[danb @dnbt777]

you can just make non euclidean gaussian splat audio visualizers

[Jake Archibald @jaffathecake]

So, Chrome's "web standard" Prompt API:

Mozilla: Opposed
WebKit: Opposed
Microsoft: Several concerns
W3C TAG: Several concerns
Developers: Mostly negative

Chrome: Ships anyway.

A sad time for web standards. But, I guess someone at Google will get promoted, so 'every cloud…'

[okazakitomohiro @oo_kk_aa]

ニャッキの伊藤有壱さんにお声掛け頂き、コマ撮りの展覧会に一作家として参加しています。私はコマ撮り分野ではない場所から活動をはじめて、デザインの視点でのコマ撮りに取り組んできましたが、今回初めてコマ撮り界の本丸の方々とご一緒でき嬉しいです。今6年目のマッチ撮影素材等を展示しています

[Alan Fregtman @alanwritescode]

🤔 @RhysSullivan https://t.co/Nj6PASlkbp are the Black Eyed Peas really coding THAT much? lol

[Alan Fregtman @alanwritescode]

@fifteen42_ hi! what happened to the otio.js? https://t.co/oXuXa140Hl why was it deleted from github? it looked good.

[Character Design References @CDReferences]

Animation by Sandro Cleuzo* ( @InspectorCleuzo ) | Molesworth

#penciltest #sakuga #genga #2danimation

[old toons @oldtoons_]

This incredible 3D background effect in 'Popeye the Sailor Meets Sindbad the Sailor' (1936) was so ahead of its time.

[Dany Bittel @DanyBittel]

My next Gaussian splat: a seven spotted ladybug in flight! #3dgs #GaussianSplatting

[Catsuka @catsuka]

"Neva", a very 2D-animated video game ♡

[Moho Animation Software @MohoAnimation]

Inspired by Quentin Blake’s multi-colored line drawings, Terence Ng Tat Mew used Moho to create this character. He has worked as a BG and visual development artist in What if, Rick and Morty, Marvel Zombies and more. Now he's proving to be an amazing 2D rigger too! #mohoanimation

[Alex Prompter @alex_prompter]

This paper from Harvard and MIT quietly answers the most important AI question nobody benchmarks properly:

Can LLMs actually discover science, or are they just good at talking about it?

The paper is called “Evaluating Large Language Models in Scientific Discovery”, and instead of asking models trivia questions, it tests something much harder:

Can models form hypotheses, design experiments, interpret results, and update beliefs like real scientists?

Here’s what the authors did differently 👇

• They evaluate LLMs across the full discovery loop hypothesis → experiment → observation → revision
• Tasks span biology, chemistry, and physics, not toy puzzles
• Models must work with incomplete data, noisy results, and false leads
• Success is measured by scientific progress, not fluency or confidence

What they found is sobering.

LLMs are decent at suggesting hypotheses, but brittle at everything that follows.

✓ They overfit to surface patterns
✓ They struggle to abandon bad hypotheses even when evidence contradicts them
✓ They confuse correlation for causation
✓ They hallucinate explanations when experiments fail
✓ They optimize for plausibility, not truth

Most striking result:

`High benchmark scores do not correlate with scientific discovery ability.`

Some top models that dominate standard reasoning tests completely fail when forced to run iterative experiments and update theories.

Why this matters:

Real science is not one-shot reasoning.

It’s feedback, failure, revision, and restraint.

LLMs today:

• Talk like scientists
• Write like scientists
• But don’t think like scientists yet

The paper’s core takeaway:

Scientific intelligence is not language intelligence.

It requires memory, hypothesis tracking, causal reasoning, and the ability to say “I was wrong.”

Until models can reliably do that, claims about “AI scientists” are mostly premature.

This paper doesn’t hype AI. It defines the gap we still need to close.

And that’s exactly why it’s important.

[Rebecca Sugar @rebeccasugar]

THIS IS A LOVE SONG 🎩🪄 animated music video out now https://t.co/x8fiEHCjlk animated by @exit73studios 🪽

[Felix & Paul Studios @felixandpaul]

🌌 Felix & Paul Studios proudly presents #InterstellarArc, opening today at #AREA15, Las Vegas!

Step aboard the Interstellar Arc and begin your journey to humanity's new home, the exoplanet Arcadia.

🎟️Get your boarding pass today on https://t.co/Y5L1OUaNDh

[Hobbes Sakuga @hobbes_sakuga]

Pencil Tests for non-traditionally animated movies.

♫ - Routine, KZA

[Akiyoshi Kitaoka @AkiyoshiKitaoka]

Vertical or horizontal gray lines appear to tilt.

[Jacob Freeman @GeForce_JacobF]

Season 8 of The Finals has a new feature called 'Smooth Destruction' that can allow destruction from other falling structures. This looks awesome.

[Ilir Aliu @IlirAliu_]

SLAM just got a serious speed boost.

Efficient LoFTR is now integrated into the @huggingface Transformers library.

It’s 2.5× faster than the original LoFTR and can even outperform the SuperPoint + LightGlue pipeline.

Image matching finds correspondences between two images taken from different angles, lighting, or scales.

It’s key for 3D computer vision tasks like:

✅ Structure from Motion (SfM)
✅ SLAM
✅ Visual Localization

Unlike traditional detector-based matchers (SuperGlue, LightGlue) that depend on a separate feature detector, LoFTR works detector-free:
•Coarse pixel-wise dense matching
•Fine-level refinement with a Transformer model

Efficient LoFTR pushes it further with:
✅ Aggregated attention + adaptive token selection
✅ Two-stage correlation for subpixel accuracy
✅ 2.5× speed boost

You can try it now in just a few lines:
pip install transformers

Thanks for sharing, @Nielsrogge!

Resources:
- model: https://t.co/xN6x1YJeJS
- docs: https://t.co/yn2Au5bq3L
- project page: https://t.co/G9ZzYMdqs2
- LoFTR: https://t.co/7ztHDHm93C