Top all-time · #2913
blog.fastforwardlabs.com
Company blog · blog.fastforwardlabs.comaidata
blog.fastforwardlabs.com is the company blog at blog.fastforwardlabs.com, writing about ai and data. Since 2014, 26 different Hacker News readers have linked it 42 times, most often “PyTorch for Recommenders 101”. The last post was in 2022, but the archive is still widely read.
Too few sampled comments (3) to say how often HN recommends it.?
Why HN links it
Cloudera Fast Forward Labs blog. The only comment about its writing calls a linked progress-in-text post a good overview. Other linking comments sit in threads on visualization and LLM agents.
Summarised by Claude from a sample of 3 HN comments that link here. Each comment is marked recommending, critical or neutral (citing without judging); how this works.
Applied machine learning research and prototypes.
Most-linked posts?
- PyTorch for Recommenders 1013 people · 3 mentions · first linked 2018-04-13
- Fingerprinting documents with steganography2 people · 3 mentions · first linked 2017-06-23
- FairML: Auditing Black-Box Predictive Models2 people · 2 mentions · first linked 2017-03-10
- Probabilistic programming: a short annotated bibliography2 people · 2 mentions · first linked 2017-10-03
What Hacker News says?
This blog post (from colleagues) covers the ideas in a little more detail http://blog.fastforwardlabs.com/2017/06/23/fingerprinting-do... and comes with proof-of-concept code https://github.com/fastforwardlabs/steganos .
Comment linking /2017/06/23/fingerprinting-documents-with-steganography.html
on “Zero-Width Characters: Invisibly fingerprinting text”Submitted The Algorithms Behind Probabilistic Programming as a story · 329 points
HN discussionThis is a good overview: https://blog.fastforwardlabs.com/2018/05/02/progress-in-text...
Comment linking /2018/05/02/progress-in-text-summarization.html
on “Show HN: A UI That Lets Readers Control How Much Information They See”Submitted Probabilistic programming from scratch as a story · 215 points
HN discussionhttp://blog.fastforwardlabs.com/2017/09/07/to-the-future.htm...
Comment linking /2017/09/07/to-the-future.html
on “Fast Forward Labs Joins Cloudera”Submitted Meta-Learners – Learning how to learn as a story · 213 points
HN discussion10 thoughts on data visualization best practices and tools: 1) For interactive visualizations of data on 3D globes, I use a mix of C++, Python (for data cleaning), and Unreal Engine (with a plugin called Cesium). An example of this is at https://youtu.be/9i-tQ8Sr80o . 2) If I am trying to put together a 3D globe that has less quality but that can be accessed by the web, I use Mapbox GL JS, D3.js, and React. An examp…
Comment linking /2019/04/29/visualizing-active-learning.html
on “Data Visualization: Choropleth maps with ggplot and R”Submitted Probabilistic Data Structure Showdown: Cuckoo Filters vs. Bloom Filters as a story · 208 points
HN discussionThe probabilities are fun (and ability to manipulate/mask/logit bias them), but small nit pick: Beam search isn't popular because it results in less human like text and takes more processing time, as a concept it sounds great in theory, but it's generally worked worse in practise compared to the next token with temperature, and results in text that is not human like, the gap is larger with larger models too, it does…
Comment linking /images/2019/05/Screen_Shot_2019_05_08_at_3_06_36_PM-1557342561886.png
on “LLM Powered Autonomous Agents”Submitted Probabilistic Programming for Anomaly Detection as a story · 125 points
HN discussionSubmitted FairML: Auditing Black-Box Predictive Models as a story · 42 points
HN discussionSubmitted Encartopedia as a story · 36 points
HN discussionSubmitted Understanding Python bytecode by implementing tail call optimization as a story · 12 points
HN discussionSubmitted Representation Learning 101 for Software Engineers as a story · 4 points
HN discussionSubmitted Federated learning: distributed machine learning with data locality and privacy as a story · 4 points
HN discussionSubmitted Why and How Convolutions Work for Video Classification as a story · 3 points
HN discussionSubmitted Interpretability in Conversation with Patrick Hall and Sameer Singh as a story · 3 points
HN discussionSubmitted Taking Prophet for a Spin as a story · 3 points
HN discussionSubmitted FairML: Auditing Black-Box Predictive Models as a story · 3 points
HN discussionSubmitted Exploring Multi-Objective Hyperparameter Optimization as a story · 2 points
HN discussionSubmitted Applications of Graph Neural Networks as a story · 2 points
HN discussionSubmitted Deep learning made easier with transfer learning as a story · 2 points
HN discussionSubmitted PyTorch for Recommenders 101 as a story · 2 points
HN discussionSubmitted PyTorch for Recommenders 101 as a story · 2 points
HN discussionSubmitted Probabilistic programming: an annotated bibliography as a story · 2 points
HN discussionSubmitted Crowdwork for Machine Learning: An Autoethnography as a story · 2 points
HN discussionSubmitted Probabilistic programming: a short annotated bibliography as a story · 2 points
HN discussionSubmitted Encartopedia – Wikipedia with a map as a story · 2 points
HN discussionSubmitted New research on interpretabiliy as a story · 2 points
HN discussionSubmitted Fingerprinting documents with steganography as a story · 2 points
HN discussion
