🤖 AI Engineer at @union_ai 📚 Hosting AI Book Club + AI Build & Learn 📹 https://xitter.cf/t.co/0MJaNC9Z4t 📅 https://xitter.cf/t.co/oOluOTzU8M
Seattle, WA
Joined June 2010
- Tweets4.1K
- Following620
- Followers1.7K
- Likes17.1K
Sage Elliott retweeted
"AI spelunking": when you vibe code the hell out of something and then do a post-hoc analysis and review of all the AI slop to try to learn WTH is going on.
#aispelunking #vibecoding
Sage Elliott retweeted
The complete reasoning-from-scratch video series is now up (and linked) here: magazine.sebastianraschka.co…
(Taking a short break but will be back with LLM model and research updates in November!)
Sage Elliott retweeted
We're hosting another hacknight this Thursday (Oct 22nd) at the @union_ai Bellevue office: This months topic is owning your AI by build agentic model factories!
@niels_ai and @GalarnykMichael are in town and will be there as well!
You'll see how Union ai & Flyte give your AI workflows a durable runtime with infrastructure as context, so agents adapt infra resources, recover from failures, and keep moving without re-running completed work. And because it all runs in your own cloud, you own the full stack end to end: your models, your data, your infrastructure, your IP.
Then we switch into hack night mode: keep building on the example, bring your own models or datasets, experiment with evals and fine-tuning, extend open models to different parts of your agent, or start something new around the same ideas.
Should be fun and i hope to you there!
Sage Elliott retweeted
dm me if you're devrel in the inference space looking for a new awesome opp and are based in the bay area.
Sage Elliott retweeted
📣 #Pandera 0.34 can now validate #PyTorch #TensorDicts, with the same schema API you'd use on a #pandas or #Polars dataframe.
I also benchmarked what validating every batch costs and what skipping it costs, and the gap is wide.
Sage Elliott retweeted
Today we're launching the Alzheimer's Translation Challenge, a global AI competition to discover new therapeutic hypotheses for Alzheimer's disease.
At its core is a new 150M cell atlas of neurons, astrocytes, and microglia across different genetic backgrounds under combinatorial perturbations, with multi-modal readouts.
The data will be made available through the AD workbench, Hugging Face and Prima Mente's modeling platform.
The challenge is led by @PrimaMente and @AlzData in collaboration with @nvidia, @huggingface, @nebiusai, Talisman Therapeutics, @UltimaGenomics, @cellanome, @PrimeIntellect, @GoodfireAI, and @boltz_bio.
In 1906, Alois Alzheimer described a new disease of the brain. After 120 years of progress, we still don't fully understand what drives this disease. We want to change that.
Participants will use the dataset to build AI models, assessed through a series of evals from general benchmarks to more complex tasks.
Top teams will be shortlisted, and their experimental hypotheses tested in Prima Mente's wet lab. Teams win when their hypotheses demonstrate the predicted molecular and functional effect.
Sage Elliott retweeted
Union: AI Infrastructure Made Easier xitter.cf/i/broadcasts/1qKDzWEaD…
Sage Elliott retweeted
Took a while, but here it is, a mega write-up on language models for text classification and, of course, Jev.
It's basically a visual guide to RNNs, CNNs, transformers, and calibration, with hands-on experiments on accuracy and efficiency.
Sage Elliott retweeted
Always fun to spot Flyte in the wild. This time, in @LilaSciences' deep dive into the infrastructure behind their AI research at Ray Summit 👀
Sage Elliott retweeted
This is why we built flyte2.
Large Fanout (250k+ parallel sub agents on union)
Dynamic and durable workflows,
Fork and replay from past runs with code changes or data changes,
And most importantly no crazy abstractions - write pure python code or now even rust code and watch it fly on union.
A Chinese developer just explained the shift from Loop Engineering to Graph Engineering better than anyone.
most people are still building agents the way that's about to be obsolete.
> why single-agent loops break and go "goal blind"
> the 4 parts of a graph: nodes, edges, state, policy
> 3 topologies that run everything: diamond, supervisor, pipeline
> Anthropic's 5 official workflow patterns
the punchline: it's not how many agents you run. it's the determinism you build with verifiers, code fallbacks, and reality anchors.
I broke the same architecture down with Kimi K3. Full A-Z guide below.
Sage Elliott retweeted
Introducing Muse Glimmer, an open-weight 30B-parameter model optimized for local, always-on agent workflows.
Muse Glimmer delivers strong performance on key agentic use cases and benchmarks compared with leading models in its size category, and is designed to run entirely on consumer hardware like a Mac or PCs with performant GPUs.
In keeping with our long tradition of sharing fundamental AI research, we’re releasing model weights under a permissive Apache 2.0 license.
🧵👇
Sage Elliott retweeted
After 18 months of writing, coding, and experimenting, Build a Reasoning Model (From Scratch) is
finally out!
My first copies just arrived! 📚
440 full-color pages. Inference scaling, reinforcement learning, and distillation from scratch.
Sage Elliott retweeted
Meet Gemma 4: our new family of open models you can run on your own hardware.
Built for advanced reasoning and agentic workflows, we’re releasing them under an Apache 2.0 license. Here’s what’s new 🧵
Sage Elliott retweeted
Hiring hiring hiring!
We @MistralAI are hiring developer advocates on my team. Join us!