Hacker News Reader

praccuon It takes 5 cloud services to hear my doorbell

I built my own motion activated stairwell lights using an ESP32 and Home Assistant. Works pretty well.

So then I decided to set up some LED strip lights for my office with really nice wireless buttons from IKEA.

I confirmed that the buttons and the lights both were zigbee compatible, but I missed that one supported only Thread and the other only Matter. So now I have two identical antennas, each handling a different protocol.

praccuon Launch HN: Discovered Materials (YC P26) – AI agents to discover new materials

Cool stuff. I first worked on ML for exploratory synthesis in 2012, and am still in related areas.

Once you have the experimental loop running, I suspect it will be quite difficult to hill climb on this task.

There will be some improvements you can make to the harness, but I suspect you'll be doing a lot of human in the loop review and providing feedback that goes back into the harness instructions.

I know it's fashionable to imagine automating the whole process, but everything I've seen is that the only systems that succeed are the ones that are augmenting an expert.

praccuon An Economy of AI Agents

This idea seems to be coming up in multiple places.

Here's one from Deepmind:

https://arxiv.org/abs/2509.10147

praccuon Tell HN: Azure outage

Many years ago (13?), I was around when Amazon moved SABLE from RAM to SSDs. A whole rack came from a single batch, and something like 128 disks went out at once.

I was an intern but everyone seemed very stressed.

praccuon Artificial intelligence gives weather forecasters a new edge

https://www.nature.com/articles/s41586-024-07744-y https://research.google/blog/fast-accurate-climate-modeling-...

praccuon Should people who quit get unemployment benefits, too?

You're very confused.

https://www.census.gov/newsroom/stories/poverty-awareness-mo...

praccuon Ask HN: What have you built with ESPHome, ESP8266 or similar hardware

I should update the post with details.

I ended up using DFRobot firebeetle because it respects sleep mode. I'm at 15 months on one charge with a 10Ah battery.

praccuon Ask HN: What have you built with ESPHome, ESP8266 or similar hardware

E Ink Todo list on my wall that pulls from Todoist, which I can update from my watch.

https://blog.praccu.com/

praccuon FDA moves to make over-the-counter hearing aids available

Massachusetts?

praccuon Vintage Startup Employee Swag?

Not for sale, I'm hijacking your thread, but I wear the heck out of my Google+ slippers.

praccuon AI is changing chemical discovery

Shameless self promotion: I wrote one of the more cited papers in the field [0], back in 2016.

A key challenge: very few labs have enough data.

Something I view as a key insight: a lot of labs are doing absurdly labor intensive exploratory synthesis without clear hypotheses guiding their work. One of our more useful tasks turned out to be interactively helping scientists refine their experiments before running them.

Another was helping scientists develop hypotheses for _why_ reactions were occuring, because they hadn't been able to build principled models that predicted which properties were predictive of reaction formation.

Going all the way to synthesis is nice, but there's a lot of lower hanging fruit involved in making scientists more effective.

[0] https://www.nature.com/articles/nature17439

praccuon Is Word Error Rate a Good Metric for Speech Recognition Models?

At Amazon I set up an evaluation approach based on whether the system completed the desired task (in that context it was "did the search result using the speech recognition return the same set of items to buy as the transcript.)

https://scholar.google.com/citations?view_op=view_citation&h...

praccuon Artificial intelligence accelerates discovery of metallic glass

Shameless plug: I published almost the same thing in a very nearby field 2 years ago:

https://www.nature.com/articles/nature17439

praccuon Google plans to reach a Quantum Computing milestone before the year is out

TLDR: DWave doesn't provide a speed-up over classical computers.

http://www.scottaaronson.com/blog/?p=3192

praccuon Computers Create Recipe for Two New Magnetic Materials

I'm not with the lab any more, but last I heard they were soliciting data from nearby but related subfields (our lab was doing mostly vanadium templated tellurides, but there are a lot of other things to explore in the space of inorganic–organic hybrids, and there are labs working on them). The problem really is data sharing; the most active collaborators were willing to give us lab note-books as long as we paid to digitize them; it was very hard to convince other labs to digitize their own notebooks. TBH I think that's the hard part of a lot of this (collecting the data).

praccuon Computers Create Recipe for Two New Magnetic Materials

We did something pretty similar in a nearby field of materials science, using support vector machines rather than linear regression and focusing on a less specific target:

http://www.nature.com/nature/journal/v533/n7601/abs/nature17...

praccuon Differentiable Neural Computers

LSTMs are very different. Think of it this way. LSTMs store information about the current problem you're solving. DNCs store information about the world.

LSTMs are designed to capture long range dependencies, e.g., "this word at the start of the sentence interacts with this word at the end of the sentence."

DNCs are designed to incorporate outside information, e.g., "i happen to know (from background knowledge) that these two people in this sentence are married"

praccuon What is chemical intuition?

As an alternative perspective: I worked in a lab that was relying heavily on intuition and heuristics for exploratory synthesis. By digitizing all of the lab's data and doing some straightforward machine learning, we were able to sufficiently improve the efficiency of the lab, compared to using intuition, and help the chemists develop a deeper understanding of the system they were studying:

http://www.nature.com/news/computer-gleans-chemical-insight-...

So, I guess my question is: to what degree is this reliance on intuition really just a lack of good data driven methods?

praccuon We’re in the Middle of a Data Engineering Talent Shortage

It's really true, though. It's brutal, ugly work with no hope of an end.

Edit: Favorite paper on the topic: http://research.google.com/pubs/pub43146.html

praccuon Computers do better than pathologists in predicting lung cancer type, severity

Agreed. I published a paper on exactly that ( augmenting scientists searching for novel materials, rather than replacing scientists entirely). One of the benefits is that you can often model simpler problems which are more tractable.

http://www.nature.com/nature/journal/v533/n7601/full/nature1...

praccuon Struggling Twitter lists over 183,000 square feet for sublease at its S.F. HQ

I think there may be a distinction:

Walmart could fill a hole in the ground with $3 billion dollars and burn it, and not care. [A bit of an exaggeration, as that's half their annual profit]

AOL acquired Time Warner for $182 billion.

praccuon Show HN: Set of trained deep learning models for computer vision

https://www.ldc.upenn.edu/

http://kingline.speechocean.com/

http://deeplearning.net/datasets/

http://www.elra.info/en/

praccuon Why Uber Engineering Switched from Postgres to MySQL

old mathematicians

praccuon Training Computers to Find Future Criminals

http://www.fatml.org/

praccuon Big Problems Facing Science

Failure data can be useful in a more fine grained way, too:

http://www.nature.com/news/computer-gleans-chemical-insight-...

praccuon Item2Vec: Neural Item Embedding for Collaborative Filtering

Thorsten Joachims gave a talk at Amazon Machine Learning Conference 2015, about doing specifically that. That may be what someone was talking about. I've been trying to find the paper related to the work, but am struggling to find it.

praccuon Item2Vec: Neural Item Embedding for Collaborative Filtering

Fascinating.

The qualitative comparison suggests that the item2vec may produce _more_ homogenous / boring results, which is kinda unfortunate; the interesting question in recommendations is how to find "aspirational" recommendations (things the shopper would not have looked for on their own).

I would really love to see an analysis that did an A/B test using more traditional CF and this, and see what the revenue lift was, because "accuracy" as measured here doesn't necessarily map onto the objective that you care about in the real world.

On the other hand, I played with using collaborative filtering to improve the personalization of language models for speech recognition for shopping, and in that context this approach sounds like it might have been super useful, because it was actually fairly challenging to get broad enough coverage of the full set of items from a small number of purchases for the purposes of language modeling. Having good embeddings would have helped a lot.

praccuon Dwarf Fortress Development

http://www.wired.com/2013/11/minecraft-book/

praccuon FAA Slaps Amazon with $350k Penalty for Shipping Violation

Of course you include stock? That's part of the cost. I know four people that just started fresh out of no-name schools for $120 including stock.

praccuon FAA Slaps Amazon with $350k Penalty for Shipping Violation

I know four people just hired making $120k, not from name-brand schools?