Location: SF (current). NYC/Philly general area acceptable. Remote okay.
email: rrenaud@gmail.com
Resume: 16 year SWE -> MLE @ Google, MS from NYU with focus on ML. Retired. Now I hack on data analysis for video game projects for fun, and I love it. I'd take crazy low compensation to do work with interesting game data sets. EG, for game balance, strategic analysis, or to improve/augment game video content.
What do y'all think about the latency/quality tradeoff with LLMs?
Human voices don't take 30 seconds to think, retrieve, research, and summarize a high quality answer. Humans are calibrated in their knowledge, they know what they understand and what they don't. They can converse in real time without bullshitting.
Frontier real time-ish LLM generated voice systems are still plagued by 2024 era LLM nonsense, like the inability to count Rs in strawberry. [1]
I'd personally love a voice interface that, constrained by the technology of today, takes the latency hit to deliver quality.
Not affiliated with Sesame, but this is what the realtime models are trying to solve. If you look at NVIDIA’s PersonaPlex release [0], it uses a duplex architecture. It’s based on Moshi [1], which aims to address this problem by allowing the model to listen and generate audio at the same time.
Cite a source. Your concrete claim is that, on average, for every $1 of subscription revenue on a monthly subscription, OpenAI and Anthropic were losing $11.50?
It seems completely implausible.
I could believe that if a $20 sub used every possible token granted, it would cost $250. But certainly almost no one was completely milking their subscription. In the same way that no one is streaming netflix literally 24/7.
I’ve been experimenting with a live win probability predictor for the 10-player arcade game Killer Queen. The goal is to predict the winner in a causal, event-by-event fashion.
Right now I’m struggling to beat a baseline LightGBM model trained on hand-engineered expert features. My attempts at using a win probability head on top of nanoGPT, treating events as tokens, have been significantly worse. I am seeing about 65% accuracy compared to the LightGBM’s 70%. That 5% gap is huge given how stochastic the early game is, and the Transformer is easily 4 OOM more expensive to train.
To bridge the gap, I’m moving to a hybrid approach. I’m feeding those expert features back in as additional tokens or auxiliary loss heads, and I am using the LightGBM model as a teacher for knowledge distillation to provide smoother gradients.
The main priority here is personalized post-game feedback. By tracking sharp swings in win probability, or $\Delta WP$, you can automatically generate high or low-light reels right after a match. It helps players see the exact moment a play was either effective or catastrophic.
There is also a clear application for automated content creation. You can use $\Delta WP$ as a heuristic to identify the actual turning points of a match for YouTube summaries without needing to manually scrub through hours of Twitch footage.
I used to play very competitively, but I've been more chill recently. I just think it's a nice problem/dataset to work with, because of the depth of my understanding of the game.
A compiler that can turn cash into improved code without round tripping a human is very cool though. As those steps can get longer and succeed more often in more difficult circumstances, what it means to be a software engineer changes a lot.
LLMs may occasionally turn bad code into better code but letting them loose on “good” or even “good enough” code is not always likely to make it “better”.
Previously, I made a live win probability model for the 5v5 arcade game Killer Queen Arcade from their game events API.
Now I am trying to use that model to make:
1. A post game instant replay that shows the most important/pivotal moments from the most recently finished game. Some arcades have a seperate display for observers, it could work well there, or as good filler between matches on twitch streams.
2. A personalized per tournament/yearly highlights recap.
If it works well, it might be a kind of tool that generalizes well for summarizing long twitch streams for Youtube.
I really enjoyed this game when I played it at Ground Kontrol in 2015 and Two-Bit Circus in 2019(?). Neat data project. I'm kinda surprised they don't add something like Stern Insider app or swipe cards to it, but it's very 80s arcadey.
Here is research about doctors interpreting test results. It seems to favor GP's view that many doctors struggle to weigh test specificity and sensitivity vs disease base rate.
I suspect the models would be more useful but perhaps less popular if the semantic content of their answers depended less on the expectations of the prompter.
reply