Michael Frew
0 followers · 286 views
on the atlas — 35
- Part 3: Intro to Policy Optimization — Spinning Up documentation6 savers
- Measuring personal growth5 savers
- Why you need a "WTF Notebook"1 savers
- Stop Acting Like You're Famous1 savers
- 2404.07794v1.pdf1 savers
- Constructors Considered Mildly Confusing1 savers
- The State of Generative AI, 2024 - by Alberto Romero1 savers
- Predictive CPU isolation of containers at Netflix | by Netflix Technology Blog | Netflix TechBlog1 savers
- Importance Sampling Explained | Built In1 savers
- Anatomy of a credit card rewards program1 savers
- 10 Years After Facebook Bought Oculus, What's Next for Meta's VR Plans? - CNET1 savers
- research!rsc: Timeline of the xz open source attack1 savers
- What we know about the xz Utils backdoor that almost infected the world | Ars Technica1 savers
- Why is observability so expensive?1 savers
- The PARA Method: The Simple System for Organizing Your Digital Life in Seconds2 savers
- transformer_attention.pdf23 savers
- Rest in motion1 savers
- 101 things I would tell my self from 10 years ago1 savers
- Must-Know Base Tips for Feature Engineering With Time Series Data | HackerNoon1 savers
- On the Dangers of Stochastic Parrots | Proceedings of the 2021 ACM Conference on Fairness, Accountability, and Transparency4 savers
- AI Research Internship Search as a CS PhD Student - by Yong1 savers
- 2301.00993v1.pdf1 savers
- 2109.10813.pdf1 savers
- Gemini and Google’s Culture – Stratechery by Ben Thompson1 savers
- Soft Actor-Critic — Spinning Up documentation4 savers
- Algorithms — Ray 2.9.31 savers
- Corporate Ozempic. If you want to understand how AI is… | by Scott Galloway | Feb, 2024 | Medium1 savers
- Changing Your Mind - by Deb Liu - Perspectives1 savers
- ScottSteven-e.pdf1 savers
- The End of 'Marriage' - The New York Times1 savers
- Curius / Onboarding2621 savers
- Theory of Change (Aaron Swartz's Raw Thought)83 savers
- The Bus Ticket Theory of Genius11 savers
- How to Think for Yourself7 savers
- a sweet humming - by jennifer tsai - jenn's journal4 savers
highlights — 6
These heuristics work for me (so far) because I have a strong bias towards novelty and exploration. Maybe one day, I’ll get tired of exploration, and these heuristics will change. When that happens, that’ll be growth.
Measuring personal growthThe hallmark of integrity is honesty, not consistency.
Changing Your Mind - by Deb Liu - PerspectivesWe raise this point because it is common for ML practitioners to interpret a loss function as a useful signal during training—”if the loss goes down, all is well.” In policy gradients, this intuition is wrong, and you should only care about average return. The loss function means nothing.
Part 3: Intro to Policy Optimization — Spinning Up documentationif you could take a year off to work on something that probably wouldn't be important but would be really interesting, what would it be?
The Bus Ticket Theory of GeniusIt's a mistake to think they were "laying the groundwork" for the discoveries they made later. There's too much intention in that metaphor. Like bus ticket collectors, they were doing it because they liked it.
The Bus Ticket Theory of Geniushe’s created this immense vertical filing cabinet in his brain of layers and layers and layers of files of information that he can draw back on now for more than 70 years worth of data
Curius / Onboarding