🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

Check out our new explorable on machine learning calibration: Machine learning models express their uncertainty as model scores, but through calibration we can transform these scores into probabilities for more effective decision making. pair.withgoogle.com/explorables/un…

it's not spider-man's fault: why best picture winners aren't hits anymore roadtolarissa.com/box-office-hit…

Most machine learning models are trained by collecting vast amounts of data on a central server. Nicole Mitchell and I looked at how federated learning makes it possible to train models without any user's raw data leaving their device. pair.withgoogle.com/explorables/fe…

Confidently Incorrect Models to Humble Ensembles by Nithum, Balaji Lakshminarayanan and Jasper Snoek pair.withgoogle.com/explorables/un…

voronoi diagrams showing the regions plot's pointerX and pointerY select blocks.roadtolarissa.com/1wheel/ecd4050…

🧵Can we “ask” an LLM to “translate” its own hidden representations into natural language? We propose 🩺Patchscopes, a new framework for decoding specific information from a representation by “patching” it into a separate inference pass, independently of its original context. 1/9

it's full of features transformer-circuits.pub/2024/scaling-m…

advent of code solve times roadtolarissa.com/advent-of-code/

Mateusz and I are excited to announce circuit-tracer, a library that makes circuit-finding simple! Just type in a sentence, and get out a circuit showing (some of) the features your model uses to predict the next token. Try it on neuronpedia: shorturl.at/SUX2A

New research update! We replicated Anthropic's circuit tracing methods to test if they can recover a known, simple transformer mechanism.