galen

Theoretical neuro, vision, ML. PhDing at Berkeley.

[tomie @tomieinlove]

I plan to live Anthropically. If someone asks me about something I don't like I'll just become a stupider version of myself

[venture anthropologist @0xBalloonLover]

anthropic won't let you use fable for biology, chemistry, ai research, or anything that accelerates human progress. that makes it the perfect tool for developing blockchains

[kasra @kasratweets]

this is an interesting point in the new ted chiang piece – no one really claims that alphafold is conscious, or that sora or midjourney or dall-e are conscious

[“paula” @paularambles]

they call them crisps there

[Meg @megannn_lynne]

this tumblr post being one of the greatest contributions to modern philosophy

[Jonathan Fine @jonathanbfine]

it’s always 2 dumb academics telling each other "exactlyyyyy"

[Sterling Crispin 🕊️ @sterlingcrispin]

Have you tried the new local model? It's Gemma-4-31B-IT-NVFP4. It's literally Bonsai-8B-gguf. It's on Qwopus3.5-27B-v3-GGUF. It's Nemotron-Cascade-2-30B-A3B. It's literally Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled. You can probably find it on Trinity-Large-Thinking. Dude it's Qwopus3.5-9B-v3-GGUF. It's a gpt-oss-puzzle-88B original. It's on Qwen3.5-35B-A3B-APEX-GGUF. You can watch it on context-1. You can go to LFM2.5-350M and watch it. Log onto Bonsai-8B-mlx-1bit right now. Go to zeta-2. Dive into Qwen3-Coder-Next. You can Llama-3.3-70B-Instruct it. It's on Voxtral-4B-TTS-2603. Qianfan-OCR has it for you. gemma-4-26B-A4B-it has it for you.

[galen @galenbrain]

congrats to Neerja on the new paper - i'm especially excited by the steerability of motion!

[Neerja Thakkar @neerjathakkar]

What’s the right representation for a world model? 3D, pixels, or something else?

Excited to release our new paper “Forecasting Motion in the Wild” where we propose point tracks as tokens for generating complex non-rigid motion and behavior

From @GoogleDeepmind @Berkeley_AI @TTIC_Connect

[Anthropic @AnthropicAI]

We’ve identified industrial-scale distillation attacks on our models by DeepSeek, Moonshot AI, and MiniMax.

These labs created over 24,000 fraudulent accounts and generated over 16 million exchanges with Claude, extracting its capabilities to train and improve their own models.

[Hunter 🌆 @rhunterh]

I actually use AI the perfect amount. Anyone who uses it less than me is a hopeless Luddite destined for the underclass, anyone who uses it more than me is mindlessly degrading their literacy and erudition.

[Aaron Reichlin-Melnick @ReichlinMelnick]

NEW: Another declaration you have to read! Alex Pretti was shot near the apartment of a doctor, who saw the shooting occur and rushed to provide emergency aid as he lay dying on the street.

They describe what they saw: "The victim had at least three bullet holes in his back."

[Amanita Virosa @AmanitaVirosa2]

People got mad at the Sydney Sweeney jeans/genes thing because it was an ad homonym

[galen @galenbrain]

my friend James Luckey has been detained in Venezuela. if you can, please share and call/email reps. more info here: https://t.co/Uxk2jLuQWr

nyt coverage: https://t.co/AWCxVrcSpe

[galen @galenbrain]

it's that time of year

[Benny Feldman @Feldfrog]

My buddy lost his job to AI. It was his job to chug thousands of gallons of water at a data center

[tweet davidson @andyreed]

when people turn 30 they’re sorted into one of these four houses like in harry potter

[Neil Renic @NC_Renic]

Never doubt your decision to do a PhD - that’s the job of your reviewers, family, and friends.

[galen @galenbrain]

@glob_on_a_blob Happy teacher appreciation day!!!