Ed Morley

CTO | Games, AI | Building worlds, products & the teams to power them | Advisor & Consultant

[Ed Morley @ed_morley]

@mitchellh This is amazing news!

[Ed Morley @ed_morley]

Extremely interesting product, which potentially unlocks a lot of use cases.

[Stefano Ermon @StefanoErmon]

Mercury 2 is live 🚀🚀

The world’s first reasoning diffusion LLM, delivering 5x faster performance than leading speed-optimized LLMs.

Watching the team turn years of research into a real product never gets old, and I’m incredibly proud of what we’ve built.

We’re just getting started on what diffusion can do for language.

[Brett Stuart @bstuartTI]

The world isn't ready for this. But I am.

Seedance 2.0 is going to drastically change filmmaking forever. I'm not being hyperbolic. This is 1 detailed prompt with 5 cuts specified and a single starter image. That's it.

It's time to start directing.

[Ed Morley @ed_morley]

Awesome!

[el.cine @EHuanglu]

OH MY FKING GODDDDDD 😱😱😱

indie filmmakers in china have already gone FULL INSANE MODE and started making movies using Seedance 2.0.. 100% AI

[Wildminder @wildmindai]

Auto rigging without manual weight painting or skeleton construction. Creators/game devs are going to love this.
SkinTokens converts skinning to discrete token sequences. uses Qwen3-0.6B for precise skeleton and weight gen across any 3D asset.
https://t.co/aVMhKmOMGh

[Ed Morley @ed_morley]

Amazing work!

[Autism Capital 🧩 @AutismCapital]

Severus Snape - ALWAYS (LIVE at Hogwarts) 🔥🔥🔥

This is a MASTERPIECE. The music, the imagery, the lyrics, the setting, the accuracy to the story, it's PERFECT. Chef's kiss. Peak AI.

📸: WickedAI (YT)

[Black Forest Labs @bfl_ai]

Introducing FLUX.2 [klein]. Blazing fast. Beautiful.

Generate stunning images in under a second while maintaining exceptional quality.

Great for fast editing, changing styles, and developing ideas from 0 → 1.

Available via API, or run it locally - Klein 4B under Apache 2.0, Klein 9B as open weights.

Try it for free in our demo app (link in the thread).

[AK @_akhaliq]

chat with papers

for any arXiv link to HF paper

you can now chat using Hugging Chat

All Hugging Face Papers now include a built-in assistant, powered by HuggingChat and the Hugging Face MCP server. It helps you quickly understand papers by answering questions, summarizing key ideas, and providing context as you browse the latest research

[DailyPapers @HuggingPapers]

InfiniDepth

Neural implicit fields for monocular depth estimation that enable arbitrary-resolution and fine-grained depth maps. Query depth at any continuous 2D coordinate, scaling from 4K to 16K and beyond.

[fal @fal]

🚨 Hunyuan 3D 3.0 is now live on fal!

🎯 3x modeling accuracy with 3.6B voxels
✨ Ultra-high resolution (1536³) photorealistic details
🎨 Text-to-3D, Image-to-3D & Sketch-to-3D
⚡ Professional-grade assets in minutes

[Ed Morley @ed_morley]

@fal Amazing to have this hosted on fal.

[AK @_akhaliq]

Microsoft just released VibeVoice-Realtime-0.5B
https://t.co/uIqp5yrZM6

[Andrej Karpathy @karpathy]

Excited to release new repo: nanochat!
(it's among the most unhinged I've written).

Unlike my earlier similar repo nanoGPT which only covered pretraining, nanochat is a minimal, from scratch, full-stack training/inference pipeline of a simple ChatGPT clone in a single, dependency-minimal codebase. You boot up a cloud GPU box, run a single script and in as little as 4 hours later you can talk to your own LLM in a ChatGPT-like web UI.

It weighs ~8,000 lines of imo quite clean code to:

- Train the tokenizer using a new Rust implementation
- Pretrain a Transformer LLM on FineWeb, evaluate CORE score across a number of metrics
- Midtrain on user-assistant conversations from SmolTalk, multiple choice questions, tool use.
- SFT, evaluate the chat model on world knowledge multiple choice (ARC-E/C, MMLU), math (GSM8K), code (HumanEval)
- RL the model optionally on GSM8K with "GRPO"
- Efficient inference the model in an Engine with KV cache, simple prefill/decode, tool use (Python interpreter in a lightweight sandbox), talk to it over CLI or ChatGPT-like WebUI.
- Write a single markdown report card, summarizing and gamifying the whole thing.

Even for as low as ~$100 in cost (~4 hours on an 8XH100 node), you can train a little ChatGPT clone that you can kind of talk to, and which can write stories/poems, answer simple questions. About ~12 hours surpasses GPT-2 CORE metric. As you further scale up towards ~$1000 (~41.6 hours of training), it quickly becomes a lot more coherent and can solve simple math/code problems and take multiple choice tests. E.g. a depth 30 model trained for 24 hours (this is about equal to FLOPs of GPT-3 Small 125M and 1/1000th of GPT-3) gets into 40s on MMLU and 70s on ARC-Easy, 20s on GSM8K, etc.

My goal is to get the full "strong baseline" stack into one cohesive, minimal, readable, hackable, maximally forkable repo. nanochat will be the capstone project of LLM101n (which is still being developed). I think it also has potential to grow into a research harness, or a benchmark, similar to nanoGPT before it. It is by no means finished, tuned or optimized (actually I think there's likely quite a bit of low-hanging fruit), but I think it's at a place where the overall skeleton is ok enough that it can go up on GitHub where all the parts of it can be improved.

Link to repo and a detailed walkthrough of the nanochat speedrun is in the reply.

[Ed Morley @ed_morley]

@ForrestTheWoods xmake is tolerable, plus you get a package manager.

[Ed Morley @ed_morley]

@Pravasith @Jonathan_Blow @ForrestTheWoods xmake is pretty good. It also has a package manager.

[Ed Morley @ed_morley]

@Jonathan_Blow Facebook/Meta got a fine for storing plain text passwords if I recall, so I guess suing a company might already be possible.

[Ed Morley @ed_morley]

@tsoding 100%

[unabatedgames @unabated_games]

Excited to drop Falls of Fortune! 🎰 This social casino mashup packs coin-dropping action, epic slots, and resort-building vibes. Team up with Maggie Wilson to turn her estate into a fortune empire. Check the screenshots 🚀 #SocialCasino #GamingNews

[Ed Morley @ed_morley]

@twominutepapers Really awesome work! Excited to try it at some point.

[Ed Morley @ed_morley]

Another great release of Tencent.
https://t.co/D1eQHzvq2l