from Hacker News

Twitter meets TensorFlow

by hurrycane on 6/14/18, 9:29 PM with 68 comments

• by llao on 6/14/18, 9:55 PM

  > Machine learning enables Twitter to drive engagement, surface content most relevant to our users, and promote healthier conversations.

  One that wants to manipulate your mind, one that echochambers your discovery, one that censors arbitrarily.

• by ralston on 6/14/18, 10:21 PM

  I always enjoy browsing the Twitter Engineering blog because of 1) the granular detail that they give 2) the concise, organized format that the information is presented, and 3) because I love their creativity. However, the first sentence of this article "Machine learning enables Twitter to drive engagement, surface content most relevant to our users, and promote healthier conversations. As part of its purpose of advancing AI for Twitter in an ethical way, Twitter Cortex is the core team responsible for facilitating machine learning endeavors within the company" is a complete turn off. Keep it technical. Leave the Marketing/PR out of it.

  - Regular blog.twitter.com/engineering reader

• by mlthoughts2018 on 6/14/18, 11:11 PM

  This is very confusing and meandering. It gives flow charts and lists of steps that don’t map to my experience building deep learning models at scale, and spends a strange amount of time passive aggressively dismissing Lua Torch and extolling virtues of TensorFlow that aren’t very important.

  As with all of these purported pipelining systems, I’m skeptical and happy to let a bunch of other people deal with the headches of making it adequately general for a few years before I’ll even start caring about grokking it for my use cases.

  In the meantime, creating build tooling, data pretreatment tooling and deployment tooling is pretty valuable for me to understand business considerations and make sure all my modeling & experimentation aren’t just time wasting ivory tower projects, particularly in terms of customizing performance characteristics on a situation-to-situation basis, free to design the deployed system without a constraint to a particular serving architecture.

  It also makes me very disinterested in applying to work for the Cortex team, because even though the article is talking about DeepBird v2 as a means to free ML engineers to do more research, it seems pretty obvious that there’s a huge surface area of maintenance and feature management for this platform. Your job is probably going to be less about research, which is scarce work that people compete over anyway.

  Possibly attractive for people who just like deep C++ platform building, which is an internal drive not often found in people wanting to solve business problems with ML models.

• by michelb on 6/15/18, 6:36 AM

  Maybe they can use ML on the user feedback to figure out what features people actually would like on the platform, instead of trying to figure out relevancy, which no company has ever successfully done. /s

  Is there a recent in-depth article somewhere about Twitter's internals? It must be frustrating working on features very few people want to use.

  I still can't edit a tweet I just posted, any video looks absolutely horrible for the first 10 seconds, the timeline is a mess, third-party developers that make interesting/much better clients are getting stomped on, and harassment is running mostly unchecked on the platform. Yet I read interesting development articles on the engineering blog. Wasted talent?

  I really like the Twitter engineering blog articles, but it seems like it's just an HR tool.

• by rotskoff on 6/15/18, 12:44 AM

  This blog post describes twitter's move from Lua Torch to Tensorflow. I am surprised to see it so highly ranked on the front page because there's very little content here. Basically, they describe the sorts of data structures they use and list a couple of advantages of Tensorflow vs. the out-of-date Lua Torch framework.

• by dmitriid on 6/15/18, 12:05 PM

  This post says all you need to know about Twitter.

  "Machine learning enables Twitter to drive engagement...".

  The very first thing they mention is engagement. They don't care about quality, or what users want, or to foster communication. They care about one thing and one thing only: engagement. More clicks, more likes, more moving around the interface.

• by mastazi on 6/15/18, 1:00 AM

  > given the migration of the Torch community from Lua to Python via PyTorch, and subsequent waning support for Lua Torch, Cortex began evaluating alternatives to Lua Torch

  I'm a bit out of the loop, has PyTorch really become so much more popular than Lua Torch, in the short time span since it launched? And is it true that most of the original Lua Torch community switched to PyTorch?

• by kieckerjan on 6/15/18, 10:46 AM

  Off topic, but the article mentions "deep learning at scale" which triggered me. Is this use of the term "at scale" something new(ish)? As far as I know "at scale" means something like "in the appropriate amount". Here it seems to be shorthand for "implemented in a scalable manner". This use seems all over the place now. Is there a native English speaker who can comment on that?

• by DrNuke on 6/14/18, 11:37 PM

  Brought my following down to 9 accounts last week and enjoying the flow again. I have always used Twitter passively, only re-tweeting 3-4 interesting stories a day. Hoping TensorFlow for healthy conversations does not spoil this sort of 24/7 breaking news from trusted sources, now. What I fear the most, is having my flow made of one tweet from sources I choose & one tweet TensorFlow suggests to me.

• by rado on 6/15/18, 3:32 PM

  What could possibly go wrong?

• by drivebyops on 6/15/18, 4:00 AM

  Did twitter drop Scala? Wonder how the story is with ML and Scala

• by sintaxi on 6/14/18, 10:55 PM

  Twitter has become a tragedy.

• by rs86 on 6/14/18, 10:10 PM

  PR sucks. It looks like PR.