Towards AI
medium.com/towards-artificial-intelligence · Group blog · on HN since 2019
Medium publication on AI, machine learning and data topics, with articles from many contributors on GANs, LLMs, SQL and vector databases.
What HN saysHN links it for individual articles, such as one on generating synthetic sequential data with GANs and another on the open-source Falcon-40B model.
31HN people shared it
3linked it in comments
40stories submitted
102story points
3 months agolast shared
2019people per year2026
Most-shared posts
- 1The Too-Small World of Artificial Intelligence2 people · 4 points · first shared 2019 · discussion on HN
- 2A Vector Database Plays Mario Kart 641 people · 11 points · first shared 2024 · 7 comments on HN
- 3Generating Synthetic Sequential Data Using GANs1 people · 8 points · first shared 2020 · discussion on HN
- 4Show HN: Google Quick Draw and CNN1 people · 7 points · first shared 2020 · discussion on HN
- 5SQL – From Intermediate to Superhero1 people · 6 points · first shared 2019 · discussion on HN
- 6Even AlphaZero Found This Game Hard – Towards AI1 people · 5 points · first shared 2020 · discussion on HN
- 7More Than 50 Python Tips and Tricks1 people · 5 points · first shared 2019 · discussion on HN
- 8Show HN: About Deep Learning, Machine Learning and Neural Networks1 people · 5 points · first shared 2020 · discussion on HN
- 9Introducing Towards AI Backers1 people · 5 points · first shared 2021 · discussion on HN
- 10Best Laptops for Machine Learning, Data Science, and Deep Learning1 people · 4 points · first shared 2020 · discussion on HN
- 11Nothing but NumPy: Creating NNs with Computational Graphs from Scratch1 people · 4 points · first shared 2019 · discussion on HN
- 12An alternative view on the future of AI. Inspired by Brave New world and 19841 people · 4 points · first shared 2019 · discussion on HN
- 13Towards AI: What is new in the AI world, and this month's editorial picks1 people · 3 points · first shared 2020 · discussion on HN
- 14MIT’s Free Online Course to Learn Julia – The Rising Star1 people · 3 points · first shared 2021 · discussion on HN
- 15How My Team of Undergrads Won a Data Science Competition1 people · 2 points · first shared 2020 · discussion on HN
What HN people wrote when they linked it
romanfll · 2026-01-15
Good catch—it's actually a hybrid approach:
1. Anomaly Detection & Visualisation: This runs 100% locally via WASM using the linear-time algorithms I shared here previously.
2. Forecasting: This hits our DriftMind API [1][2].
We designed the API to be transient-only. The data is processed in-memory for the forecast and immediately discarded; absolutely nothing is persisted to disk or used for training. We wanted to keep the browser lightweight while still offering the heavy-duty forecasting from our core engine
[1] https://thingbook.io/doc/devGuide.html
[2] https://medium.com/towards-artificial-intelligence/reflexive-memory-a-…
thruflo22 · 2020-07-02
Very cool!
We’re using GANs to generate synthetic transactional data that preserves temporary and causal correlations [0].
[0] friends link to avoid paywall: https://medium.com/towards-artificial-intelligence/generating-syntheti…