Comments URL: https://news.ycombinator.com/item?id=44147441

Points: 2

# Comments: 0

1. In practical scenarios, how do you know if x' is really drawn from p(x)? Even if you could compute log p(x') under the true data distribution, you can only verify that the support for x' is non-zero. one sample is not enough to tell you if x' drawn from p(x).

2. In high dimensional settings, x' that is not exactly equal to an example within the training set can have arbitrarily high generalization error. here's a criminally under-cited paper discussing this: https://arxiv.org/abs/1801.02774

Comments URL: https://news.ycombinator.com/item?id=41575691

Points: 3

# Comments: 0

Railway tracks have crushed stones, commonly known as ballast, alongside them for several important reasons. Here are the main reasons for using ballast on railway tracks:

Stability and Load Distribution: Ballast provides stability to the railway tracks and distributes the load of the trains evenly. The crushed stones interlock with each other and form a stable base for the tracks. This helps prevent the tracks from shifting or sinking under the weight of the trains.

Drainage: Ballast allows for effective drainage of water from the tracks. The open spaces between the crushed stones allow water to flow away from the tracks, preventing the accumulation of water. Proper drainage is essential to maintain the stability of the tracks and prevent damage caused by water-related issues like erosion or track bed saturation.

Track Alignment and Adjustment: Ballast allows for easy alignment and adjustment of the tracks. The crushed stones can be added or removed as needed to maintain the proper track alignment and ensure a smooth ride for trains. This flexibility is especially important during track maintenance or when new tracks are being laid.

Noise and Vibration Damping: Ballast helps in reducing noise and vibrations generated by passing trains. The layer of crushed stones absorbs and dampens the vibrations, minimizing the impact on the surrounding environment and nearby structures.

Track Maintenance: Ballast provides a protective layer for the tracks. It acts as a barrier between the track infrastructure and the underlying soil, preventing soil movement or erosion that could damage the tracks. Additionally, ballast makes it easier to detect and repair any issues with the track, such as loose fastenings or track bed settlement.

Overall, the use of ballast alongside railway tracks is crucial for maintaining the stability, alignment, drainage, and longevity of the tracks, ensuring safe and efficient train operations.

1X is an engineering and robotics company producing androids capable of human-like movements and behaviors. The company was founded in 2014 and is headquartered in Norway, with over 50 employees globally. 1X's mission is to create robots with practical, real-world applications to augment human labor globally. We recently announced a $23.5M Series A2 funding led by OpenAI (https://1xtech.medium.com/1x-raises-23-5m-in-series-a2-fundi...)

Open Positions:

- Senior DevOps Engineer | Full-Time | Onsite | Oslo, Norway https://1x.tech/#job-1112510

- Electronics Hardware Engineer | Full-Time | Onsite | Oslo, Norway https://1x.tech/#job-1079027

- Full-Stack AI Resident | Intern | Onsite | Bay Area, CA, USA https://1x.tech/#job-1079027

Comments URL: https://news.ycombinator.com/item?id=35671645

Points: 2

# Comments: 0

DistBelief was tricky to program because it was written all in C++ and Protobufs IIRC. The development of TFv1 preceded my time at Google, so I can't comment on who contributed what.

When I joined Brain in 2016, I had thought the idea of training billion/trillion-parameter sparsely gated mixtures of experts was a huge waste of resources, and that the idea was incredibly naive. But it turns out he was right, and it would take ~6 more years before that was abundantly obvious to the rest of the research community.

Here's his scholar page (H index of 94) https://scholar.google.com/citations?hl=en&user=NMS69lQAAAAJ...

As a leader, he also managed the development of TensorFlow and TPU. Consider the context / time frame - the year is 2014/2015 and a lot of academics still don't believe deep learning works. Jeff pivots a >100-person org to go all-in on deep learning, invest in an upgraded version of Theano (TF) and then give it away to the community for free, and develop Google's own training chip to compete with Nvidia. These are highly non-obvious ideas that show much more spine & vision than most tech leaders. Not to mention he designed & coded large parts of TF himself!

And before that, he was doing systems engineering on non-ML stuff. It's rare to pivot as a very senior-level engineer to a completely new field and then do what he did.

Jeff certainly has made mistakes as a leader (failing to translate Google Brain's numerous fundamental breakthroughs to more ambitious AI products, and consolidating the redundant big model efforts in google research) but I would consider his high level directional bets to be incredibly prescient.

Comments URL: https://news.ycombinator.com/item?id=35311640

Points: 10

# Comments: 0

Comments URL: https://news.ycombinator.com/item?id=32287931

Points: 61

# Comments: 3

Comments URL: https://news.ycombinator.com/item?id=32027998

Points: 18

# Comments: 2