How to Evaluate LLM Summarization

medium.com/data-science/how-to-evaluate-llm-summarization-18a040c3905d

Evaluating LLMs for Text Summarization: An Introduction

www.sei.cmu.edu/blog/evaluating-llms-for-text-summarization-introduction/

How I Built Agent Skills for Claude Code

dev.to/nunc/how-i-built-agent-skills-for-claude-code-oj4

The Day Google Made Coding Obsolete: How Gemini 3.0 and Antigravity Force Us All to Evolve | by Adham Khaled | in Towards AI - Freedium

freedium-mirror.cfd/https://pub.towardsai.net/the-day-google-made-coding-obsolete-how-gemini-3-0-and-antigravity-force-us-all-to-evolve-447ebdca6c27

Ten stupid simple behaviours that make people respect you more | by Alex Mathers - Freedium

freedium-mirror.cfd/https://iamalexmathers.medium.com/ten-stupid-simple-behaviours-that-make-people-respect-you-more-a63d72b3f472

OpenAI Is Getting Utterly Desperate | by Will Lockett - Freedium

freedium-mirror.cfd/https://wlockett.medium.com/openai-is-getting-utterly-desperate-5b976da17872

You Have No Idea How Screwed OpenAI Is | by Alberto Romero - Freedium

freedium-mirror.cfd/https://albertoromgar.medium.com/you-have-no-idea-how-screwed-openai-is-9481fe33f1db

Stanford Just Killed Prompt Engineering With 8 Words (And I Can't Believe It Worked) | by Adham Khaled | in Generative AI - Freedium

freedium-mirror.cfd/https://generativeai.pub/stanford-just-killed-prompt-engineering-with-8-words-and-i-cant-believe-it-worked-8349d6524d2b

AI Pullback Has Officially Started | by Will Lockett - Freedium

freedium-mirror.cfd/https://wlockett.medium.com/ai-pullback-has-officially-started-fb6dfa5e4128

The 3-Level Prompting System That Makes AI Insanely Useful | by Eva Keiffenheim | in Age of Awareness - Freedium

freedium-mirror.cfd/https://medium.com/age-of-awareness/the-3-level-prompting-system-that-makes-ai-insanely-useful-c37f9e64d547

I have built around 300 agents, worked at 5 startups. Here's what I learnt about AI Agent | by Yashwanth Sai - Freedium

freedium.cfd/https://medium.com/@theyashwanthsai/i-have-built-around-300-agents-worked-at-5-startups-heres-what-i-learnt-about-ai-agent-e911ffa62682

The Only ChatGPT Prompt that Matters. | by Jordan Gibbs - Freedium

freedium.cfd/https://medium.com/@jordan_gibbs/the-only-chatgpt-prompt-that-matters-f16dd85e43b3

Building the Entire RAG Ecosystem and Optimizing Every Component

levelup.gitconnected.com/building-the-entire-rag-ecosystem-and-optimizing-every-component-8f23349b96a4

ChatGPT vs Claude vs Gemini: The Best AI Model for Each Use Case in 2025

creatoreconomy.so/p/chatgpt-vs-claude-vs-gemini-the-best-ai-model-for-each-use-case-2025

99% of Developers are Using Claude Wrong (How to Be The 1%) | by Alex Dunlop | in Vibe Coding - Freedium

freedium.cfd/https://medium.com/vibe-coding/99-of-developers-are-using-claude-wrong-how-to-be-the-1-9abfec9cb178

How to Build a Boring AI Startup That Quietly Hits $10M ARR | by Divad Sanders | in The Startup - Freedium

freedium.cfd/https://medium.com/swlh/how-to-build-a-boring-ai-startup-that-quietly-hits-10m-arr-1a92285f0cf8

FM-Intent: Predicting User Session Intent with Hierarchical Multi-Task Learning

netflixtechblog.com/fm-intent-predicting-user-session-intent-with-hierarchical-multi-task-learning-94c75e18f4b8

5 Industries AI Will Completely Takeover by 2026 | by Mr Tony Momoh | in AI Mind - Freedium

freedium.cfd/https://pub.aimind.so/5-industries-ai-will-completely-takeover-by-2026-d16d36b70cce

Zwilling.pdf

content.wolfram.com/sites/19/2013/04/Zwilling.pdf

Zero-Inflated Negative Binomial Regression | R Data Analysis Examples

stats.oarc.ucla.edu/r/dae/zinb/

中国传媒大学《游戏心理学》MOOC笔记

blog.lycheeee.top/posts/62a85fc4/

为什么人会熬夜玩游戏？——在产品设计中刺激“多巴胺” – 人人都是产品经理

www.woshipm.com/pd/4409952.html

How to Apply for a Visa | Consulate-General of Japan in Seattle

www.seattle.us.emb-japan.go.jp/itpr_en/VISA_Jurisdiction.html

arxiv.org/pdf/2008.11619

A New Coefficient of Correlation | Hacker News

news.ycombinator.com/item?id=29687613

A New Coefficient of Correlation

medium.com/data-science/a-new-coefficient-of-correlation-64ae4f260310

Reflections on modern methods: demystifying robust standard errors for epidemiologists - Robust SE. manuscript. in White Rose.pdf

eprints.whiterose.ac.uk/169886/3/Robust%20SE.%20manuscript.%20in%20White%20Rose.pdf

Introducing Impressions at Netflix

netflixtechblog.com/introducing-impressions-at-netflix-e2b67c88c9fb

Zero-Inflated Negative Binomial Regression - Zero-Inflated_Negative_Binomial_Regression.pdf

www.ncss.com/wp-content/themes/ncss/pdf/Procedures/NCSS/Zero-Inflated_Negative_Binomial_Regression.pdf

Introduction to Pyro — Pyro Tutorials 1.8.4 documentation

pyro.ai/examples/intro_long.html

SVI Part I: An Introduction to Stochastic Variational Inference in Pyro — Pyro Tutorials 1.9.1 documentation

pyro.ai/examples/svi_part_i.html

Designing difference in differences: lessons from concealed carry laws in crime

causalinf.substack.com/p/designing-difference-in-differences

Hallucinations, Errors, and Dreams

medium.com/@colin.fraser/hallucinations-errors-and-dreams-c281a66f3c35

Generative AI is a hammer and no one knows what is and isn’t a nail

medium.com/@colin.fraser/generative-ai-is-a-hammer-and-no-one-knows-what-is-and-isnt-a-nail-4c7f3f0911aa

2410.09267v1.pdf

arxiv.org/pdf/2410.09267

2103.06392v3.pdf

arxiv.org/pdf/2103.06392

译介丨宫本茂《纽约客》访谈：想要创造一个更加友好的世界 | 机核 GCORES

www.gcores.com/articles/132249

lecture11.pdf

people.eecs.berkeley.edu/~jordan/courses/260-spring10/lectures/lecture11.pdf

Bayesian Adaptive Methods for Clinical Trials (Chapman & Hall/CRC Biostatistics Series) - 21.pdf

ndl.ethernet.edu.et/bitstream/123456789/43897/1/21.pdf

The utility of Bayesian predictive probabilities for interim monitoring of clinical trials

www.ncbi.nlm.nih.gov/pmc/articles/PMC4247348/

An Introduction to Markov Chain Monte Carlo

jaketae.github.io/study/MCMC/

What is Gibbs Sampling? - GeeksforGeeks

www.geeksforgeeks.org/what-is-gibbs-sampling/

How UMAP Works — umap 0.5 documentation

umap-learn.readthedocs.io/en/latest/how_umap_works.html

jeffreys.pdf

www2.stat.duke.edu/courses/Fall11/sta114/jeffreys.pdf

The Bayesian Design of Adaptive Clinical Trials

www.ncbi.nlm.nih.gov/pmc/articles/PMC7826635/

Adaptive designs in clinical trials: why use them, and how to run and report them - BMC Medicine

bmcmedicine.biomedcentral.com/articles/10.1186/s12916-018-1017-7

Chapter 21 - A Gallery of Rogues: Other Methods | The Effect

theeffectbook.net/ch-TheEdge.html

Synthetic Difference-in-Differences Estimation - dp15907.pdf

docs.iza.org/dp15907.pdf

1712.09089v10.pdf

arxiv.org/pdf/1712.09089

Conformal Inference Tutorial

cdsamii.github.io/cds-demos/conformal/conformal-tutorial.html

1604.04173v2.pdf

arxiv.org/pdf/1604.04173