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

[Collin Gross @CollinGrossWx]

Impressive NASA visualization showing the extensive transport of wildfire smoke from Canada and the western U.S. from mid-July to August 5th.

Smoke intensity and movement are depicted using NASA’s GEOS-CAM modeling system.

[Bilawal Sidhu @bilawalsidhu]

Progress update: figuring out the 3D location of every photo taken at TED with attribution. It's starting to feel magical -- makes me wonder what experiences are possible if we could do this for every live event ever.

[Iker J. de los Mozos @soyposmoderno]

Fresh off the GNM launch (https://t.co/ipjLFnYClm), here’s a closer look at what you can do with it!

GNM is fully open-source, meaning that you can build right on top of it. Here I’m using normalized vertex groups in Blender to mask different regions while randomizing identities.

And if you want to go beyond realism you can always push these settings further to create stylized characters.

[VoxelKei @VoxelKei]

3D Gaussian Splattingの新しい見せ方を作りました。その名も Inversphere.
2Dのリトルプラネットと違い、空間ごと球面反転しています。ガラス玉に入れる従来の見せ方は球で「切り取る」のに対して、これは球の中へ「折り込む」ので360度の景色が無限遠まで立体で入っています。
#3DGS

[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 Veremeyenko @alex_verem]

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