The new pypi looks amazing! Example: pypi.org/project/ipdb/

🚀 Today, we've open-sourced Rivet, a game-changer for #AI agents! We just launched our first AI agent at Ironclad. But I almost gave up on it, until Andy build v0 of Rivet and showed me what was possible. Let us know what you think! rivet.ironcladapp.com

"The Bias-Variance Dilemma" from Daniel Geng and Shannon Shih: buff.ly/2uP1t2N #machinelearning

"The Business of Artificial Intelligence" from Erik Brynjolfsson buff.ly/2f2qh20

Useful tips from Slav Ivanov for when your model isn't working: buff.ly/2vZ3wQz #machinelearning #deeplearning

Goog extends 'Wide and Deep' to higher order feature interactions. Notes from Jim Fleming's #deeplearningsf my.memo.ai/external/vJ-iB…

When you get rounding errors in your package versions: "html5lib 0.999999999" pypi.python.org/pypi/html5lib

Machine learning is a big deal -- John Deere is paying $305 million to buy a 60-person Silicon Valley tech startup axios.com/john-deere-is-…

New post from BAIR on their paper "Learning to Optimize" buff.ly/2jEYHcY #DeepLearning #MachineLearning

Simple guide to interpreting random forests from Pivotal buff.ly/2xl1wob #MachineLearning

Useful guide to the Gumbel-max trick from Tim Vieira buff.ly/2hgy1dX #MachineLearning

blog post by Sanjay Krishnan: Learning Long Duration Sequential Task Structure From Demonstrations bair.berkeley.edu/blog/2017/10/1…

Reading group for AlphaGo Zero paper meetup.com/deep-learning-…

I wanted a fun weekend project so I'm recreating the env from: "It Takes Two Neurons to Ride a Bicycle": citeseerx.ist.psu.edu/viewdoc/downlo…

I got the bike hooked up to Bullet and parts of the Gym env setup too!

I'll need to perturb the bike at the beginning of the episodes, otherwise it's too easy:

"My GAN is suing me..." x.com/jackclarkSF/st…

That reads like a queued tweet from December. Especially in contrast to FB blocking crypto ads yesterday, which feels like the better move: x.com/jack/status/95…

Essential reading (2016) to get started with self-play ML using TensorFlow. The leap from backgammon to chess/go was astonishing. From there to sport simulation is closer than you think x.com/jimmfleming/st…

Tracing the front wheel of the bicycle over several episodes. I suspect the steering column is a little stiff since the dynamics look somewhat different from the paper.