Cory Slater (@corslater) header
Cory Slater (@corslater) profile picture

Just out here looking for the looker. Producting product products @PostHog

Seattle, WA
Joined August 2009
Photo by Cory Slater (@corslater)Photo by Cory Slater (@corslater)Photo by Cory Slater (@corslater)Photo by Cory Slater (@corslater)Photo by Cory Slater (@corslater)Photo by Cory Slater (@corslater)Photo by Cory Slater (@corslater)Photo by Cory Slater (@corslater)Photo by Cory Slater (@corslater)Photo by Cory Slater (@corslater)
Cory Slater retweeted
Introducing Munari: data and operator quality scoring for robotics. Robotics teams need training data, but collection operations often lack a consistent measure of the quality of their demonstrations. Thousands of paid operator hours, with limited feedback on how to make the next hour better. We’re changing that with operator and episode quality scoring. Munari lets you: ➤ Evaluate every human demonstration against your definition of good ➤ Turn those scores into actionable feedback that improves how operators collect data ➤ Measure progress across sessions and track quality fluctuations over time This creates a feedback loop that compounds: collect, score, coach, and measure what improves. Operators learn from each session, teams refine their collection process, and the same human hours produce more usable training data. This measurement layer is the first step toward training models for reliable deployment. Making sure data teams understand what good looks like and how to consistently produce it. Our longer-term vision is to help teams benchmark and collect the right data for a specific job, environment, and robot. Knowing what you want to deploy can guide what you collect and how you evaluate it. Better data collection. Better robots. We’re already live with early partners and now opening a few more spots for pilot customers. If you’re collecting data or deploying robots, we’d love to chat!
43
19
7
175
16,274
How can we unlock generalized reasoning? ⚡️Introducing Energy-Based Transformers (EBTs), an approach that out-scales (feed-forward) transformers and unlocks generalized reasoning/thinking on any modality/problem without rewards. TLDR: - EBTs are the first model to outscale the Transformer++ during pretraining across modalities and with respect to data, parameters, FLOPs, depth, etc - EBTs achieve a +29% improvement over the Transformer++ at test-time via thinking longer - EBTs exhibit better generalization than existing models during inference 🧵Thread:
50
258
51
1,651
356,702
Cory Slater retweeted
The way that OpenAI uses user feedback to train the model is misguided and will inevitably lead to further issues like this one. Supervised fine-tuning (SFT) on "ideal" responses is simply teaching the model via imitation, which is fine as far as it goes. But it's not enough...
5
5
1
149
9,722
Awesome work from @ReactiveBayes . We took this new notebook example and made it into Julia script with more visualizations and animations. github.com/docxology/RxInfer…
🚀 An update from the RxInfer team! We've added an experimental implementation of the Recurrent Switching Linear Dynamical Systems (RSLDS) model, inspired by Linderman et al.'s work (arxiv.org/abs/1610.08466) Check it out here examples.rxinfer.com/categor… #BayesianInference #RxInfer
4
23
1,112
Attention has been the key component for most advances in LLMs, but it can’t scale to long context. Does this mean we need to find an alternative? Presenting Titans: a new architecture with attention and a meta in-context memory that learns how to memorize at test time. Titans are more effective than Transformers and modern linear RNNs, and can effectively scale to larger than 2M context window, with better performance than ultra-large models (e.g., GPT4, Llama3-80B).
80
563
117
3,350
640,205
This Post is from an account that no longer exists. Learn more
6
13
1,679
LLMs and optimizing an organization's OODA loop is going to be huge. Are you ready?
3
4
1
23
2,724
Cory Slater retweeted
The TTT layer, as a new mechanism to compress information and model memory, can be a simple replacement for the self-attention layer in Transformer. Recall Transformer explicitly stores all input tokens. If you believe that training neural networks is a good way to compress information in general, then it will make sense to train a neural network to compress all these tokens.
2
10
76
16,209
There it is. 'First Principles AI' to emulate a biological process at scale. More coming. Sci-fi becoming sci-fact @Lux_Capital
Replying to @wolfejosh
6/ We’re excited to unveil historic new company EvolutionaryScale and their release of ESM3—a frontier language model for the life sciences that advances our ability to program and create with the code of life. ESM3 takes a step towards the future where AI is a tool to engineer biology from first principles in the same way we engineer structures, machines and microchips, and write computer programs.
1
6
4,594
Cory Slater retweeted
We have trained ESM3 and we're excited to introduce EvolutionaryScale. ESM3 is a generative language model for programming biology. In experiments, we found ESM3 can simulate 500M years of evolution to generate new fluorescent proteins. Read more: evolutionaryscale.ai/blog/es…
125
781
281
3,284
1,538,212
Cory Slater retweeted
remember when a study in the nature journal deconstructed all of politics and it really just came down to this?
587
4,421
603
52,165
6,990,617
Cory Slater retweeted
1/ Quick thread 🧵important new paper 📜from @sfiscience on the THERMODYNAMICS of COMPUTATION... Ever wondered why your gadgets get warm after using them for a while? As with cells🧫, brains🧠 and laptops💻––it's all about energy use and heat🔥....
8
19
2
83
58,486
Cory Slater retweeted
1/ NEW–– just released. Lux Q1 2024 Letter to LPs…
15
42
6
460
215,023
This type of dark pattern should be illegal. Shame on you @TaxAct for making it impossible to unsubscribe from marketing emails. I tried in multiple browsers with multiple sessions. The only button that worked was "No".
2
93
Ground breaking. Speechless.
Natural Induction: Spontaneous adaptive organisation without natural selection biorxiv.org/cgi/content/shor… #biorxiv_evobio
65
Sharing a bit more about Reflect Orbital today. @4TristanS and I are developing a constellation of revolutionary satellites to sell sunlight to thousands of solar farms after dark. We think sunlight is the new oil and space is ready to support energy infrastructure. This airborne test was the last piece needed before we launch above the atmosphere. 🧵🧵(1/6)
502
705
745
4,436
2,333,845
Cory Slater retweeted
Fun little paper to appear tonight on the arXiv. How to do Hamiltonian Monte Carlo on digital Quantum Computers. As physics-based probabilistic ML accelerators are on the horizon, important to test how QC's could try to compete. Best way to predict future is to invent it.🙂
21
74
17
607
704,215
Cory Slater retweeted
We in energy should look to aerospace and defense as inspiration on how to defeat a regulatory paradigm that inflates costs Rate basing = cost-plus government contracts Exiting incumbent incentive structures are the only way to drastically lower costs and make things like private space flight or reliable high VRE delivery possible – at Queens, NY
defense & space economy - not just vibey on the venture side
3
2
2
13
4,736
Cory Slater retweeted
Take a look at Lux family co @VariantBio… Partnering with growing number of tribes, indigenous groups, local populations for some of the most interesting as yet unknown undiscovered druggable targets from OUTLIER humans with OUTLIER traits in OUTLIER parts of the world…
Every mutation that could exist, does exist. That has only been true for ~200 years. Most beneficial variants just haven't had the time to become ubiquitous. But now, at least 50 people in the world have every possible mutation in the human genome.
2
2
18
9,249
Cory Slater retweeted
Extraordinary paper by Joana Xavier @joanarcxavier + longtime @sfiscience Stuart Kauffman on ORIGIN OF LIFE via auto-catalytic networks (from increasing complexity of combinatorial possibilities of elements > molecules > chemical (auto)catalysis… full paper via @royalsociety royalsocietypublishing.org/d…
6
7
27
10,289