技术博客与 newsletter feed · Eugene Yan · Writing
| 热搜话题 | 最高排名 | 首次上榜 | 离榜时间 | 在榜时长 | 上榜次数 |
|---|---|---|---|---|---|
01 AI Engineer 2026 - Using LLMs to Secure Source Code Sharing what we learned from Project Glasswing. | #100:00 达到 | 00:00首次采集时已在榜 | —结束时仍在榜 | 7小时37分累计在榜 | 1无重入 |
02 Patterns for Building Cybersecurity Evals A sandboxed target, inputs that influence task difficulty, tools, and a grader. | #200:00 达到 | 00:00首次采集时已在榜 | —结束时仍在榜 | 7小时37分累计在榜 | 1无重入 |
03 Using LLMs to Secure Source Code Build a threat model, discover vulnerabilities, verify, triage, and patch. | #300:00 达到 | 00:00首次采集时已在榜 | —结束时仍在榜 | 7小时37分累计在榜 | 1无重入 |
04 How to Work and Compound with AI Context as infra, taste as config, verify for autonomy, scale via delegation, close the loop. | #400:00 达到 | 00:00首次采集时已在榜 | —结束时仍在榜 | 7小时37分累计在榜 | 1无重入 |
05 2025 Year in Review An eventful year of progress in health and career, while making time for travel and reflection. | #500:00 达到 | 00:00首次采集时已在榜 | —结束时仍在榜 | 7小时37分累计在榜 | 1无重入 |
06 Product Evals in Three Simple Steps Label some data, align LLM-evaluators, and run the eval harness with each change. | #600:00 达到 | 00:00首次采集时已在榜 | —结束时仍在榜 | 7小时37分累计在榜 | 1无重入 |
07 Advice for New Principal Tech ICs (i.e., Notes to Myself) Based on what I've learned from role models and mentors in Amazon | #700:00 达到 | 00:00首次采集时已在榜 | —结束时仍在榜 | 7小时37分累计在榜 | 1无重入 |
08 Training an LLM-RecSys Hybrid for Steerable Recs with Semantic IDs An LLM that can converse in English & item IDs, and make recommendations w/o retrieval or tools. | #800:00 达到 | 00:00首次采集时已在榜 | —结束时仍在榜 | 7小时37分累计在榜 | 1无重入 |
09 Evaluating Long-Context Question & Answer Systems Evaluation metrics, how to build eval datasets, eval methodology, and a review of several benchmarks. | #900:00 达到 | 00:00首次采集时已在榜 | —结束时仍在榜 | 7小时37分累计在榜 | 1无重入 |
10 AI Engineer 2025 - Improving RecSys & Search with LLM techniques Recsys & search are converging with LLMs via semantic IDs, data augmentation, and unified foundation models. | #1000:00 达到 | 00:00首次采集时已在榜 | —结束时仍在榜 | 7小时37分累计在榜 | 1无重入 |
11 Exceptional Leadership: Some Qualities, Behaviors, and Styles What makes a good leader? What do good leaders do? And commando, soldier, and police leadership. | #1100:00 达到 | 00:00首次采集时已在榜 | —结束时仍在榜 | 7小时37分累计在榜 | 1无重入 |
12 Building News Agents for Daily News Recaps with MCP, Q, and tmux Learning to automate simple agentic workflows with Amazon Q CLI, Anthropic MCP, and tmux. | #1200:00 达到 | 00:00首次采集时已在榜 | —结束时仍在榜 | 7小时37分累计在榜 | 1无重入 |
13 An LLM-as-Judge Won't Save The Product—Fixing Your Process Will Applying the scientific method, building via eval-driven development, and monitoring AI output. | #1300:00 达到 | 00:00首次采集时已在榜 | —结束时仍在榜 | 7小时37分累计在榜 | 1无重入 |
14 Frequently Asked Questions about My Writing Process How I started, why I write, who I write for, how I write, and more. | #1400:00 达到 | 00:00首次采集时已在榜 | —结束时仍在榜 | 7小时37分累计在榜 | 1无重入 |
15 NVIDIA GTC 2025 - Building LLM-Powered Applications Chip Huyen and I share what we've learned, best practices, and insights at NVIDIA GTC 2025. | #1500:00 达到 | 00:00首次采集时已在榜 | —结束时仍在榜 | 7小时37分累计在榜 | 1无重入 |
16 Improving Recommendation Systems & Search in the Age of LLMs Model architectures, data generation, training paradigms, and unified frameworks inspired by LLMs. | #1600:00 达到 | 00:00首次采集时已在榜 | —结束时仍在榜 | 7小时37分累计在榜 | 1无重入 |
17 Building AI Reading Club: Features & Behind the Scenes Exploring how an AI-powered reading experience could look like. | #1700:00 达到 | 00:00首次采集时已在榜 | —结束时仍在榜 | 7小时37分累计在榜 | 1无重入 |
18 2024 Year in Review A peaceful year of steady progress on my craft and health. | #1800:00 达到 | 00:00首次采集时已在榜 | —结束时仍在榜 | 7小时37分累计在榜 | 1无重入 |
19 A Spark of the Anti-AI Backlash (on Bluesky) How the sharing of 1M Bluesky posts uncovered the strong anti-AI sentiment on Bluesky. | #1900:00 达到 | 00:00首次采集时已在榜 | —结束时仍在榜 | 7小时37分累计在榜 | 1无重入 |
20 Seemingly Paradoxical Rules of Writing With regard to writing, there are many rules and also no rules at all. | #2000:00 达到 | 00:00首次采集时已在榜 | —结束时仍在榜 | 7小时37分累计在榜 | 1无重入 |
21 How to Run a Weekly Paper Club (and Build a Learning Community) Benefits of running a weekly paper club, how to start one, and how to read and facilitate papers. | #2100:00 达到 | 00:00首次采集时已在榜 | —结束时仍在榜 | 7小时37分累计在榜 | 1无重入 |
22 My Minimal MacBook Pro Setup Guide Setting up my new MacBook Pro from scratch | #2200:00 达到 | 00:00首次采集时已在榜 | —结束时仍在榜 | 7小时37分累计在榜 | 1无重入 |
23 39 Lessons on Building ML Systems, Scaling, Execution, and More ML systems, production & scaling, execution & collaboration, building for users, conference etiquette. | #2300:00 达到 | 00:00首次采集时已在榜 | —结束时仍在榜 | 7小时37分累计在榜 | 1无重入 |
24 AlignEval: Building an App to Make Evals Easy, Fun, and Automated Look at and label your data, build and evaluate your LLM-evaluator, and optimize it against your labels. | #2400:00 达到 | 00:00首次采集时已在榜 | —结束时仍在榜 | 7小时37分累计在榜 | 1无重入 |
25 Weights & Biases LLM-Evaluator Hackathon - Hackathon Judge Being a human judge at the Weights & Biases LLM-as-a-Judge Hackathon | #2500:00 达到 | 00:00首次采集时已在榜 | —结束时仍在榜 | 7小时37分累计在榜 | 1无重入 |
26 Building the Same App Using Various Web Frameworks FastAPI, FastHTML, Next.js, SvelteKit, and thoughts on how coding assistants influence builders' choices. | #2600:00 达到 | 00:00首次采集时已在榜 | —结束时仍在榜 | 7小时37分累计在榜 | 1无重入 |
27 Evaluating the Effectiveness of LLM-Evaluators (aka LLM-as-Judge) Use cases, techniques, alignment, finetuning, and critiques against LLM-evaluators. | #2700:00 达到 | 00:00首次采集时已在榜 | —结束时仍在榜 | 7小时37分累计在榜 | 1无重入 |
28 How to Interview and Hire ML/AI Engineers What to interview for, how to structure the phone screen, interview loop, and debrief, and a few tips. | #2800:00 达到 | 00:00首次采集时已在榜 | —结束时仍在榜 | 7小时37分累计在榜 | 1无重入 |
29 AI Engineer 2024 Keynote - What We Learned from a Year of LLMs Special double-feature closing keynote from the 6 authors of the hit O'Reilly article on Applied LLMs. | #2900:00 达到 | 00:00首次采集时已在榜 | —结束时仍在榜 | 7小时37分累计在榜 | 1无重入 |
30 Netflix PRS 2024 - Applying LLMs to Recommendation Experiences Challenges and lessons from deploying LLM experiences: evals, scalability, guardrails. | #3000:00 达到 | 00:00首次采集时已在榜 | —结束时仍在榜 | 7小时37分累计在榜 | 1无重入 |
31 Prompting Fundamentals and How to Apply them Effectively Structured input/output, prefilling, n-shots prompting, chain-of-thought, reducing hallucinations, etc. | #3100:00 达到 | 00:00首次采集时已在榜 | —结束时仍在榜 | 7小时37分累计在榜 | 1无重入 |
32 What We've Learned From A Year of Building with LLMs From the tactical nuts & bolts to the operational day-to-day to the long-term business strategy. | #3200:00 达到 | 00:00首次采集时已在榜 | —结束时仍在榜 | 7小时37分累计在榜 | 1无重入 |
33 Building an AI Coach to Help Tame My Monkey Mind Building an AI coach with speech-to-text, text-to-speech, an LLM, and a virtual number. | #3300:00 达到 | 00:00首次采集时已在榜 | —结束时仍在榜 | 7小时37分累计在榜 | 1无重入 |
34 Task-Specific LLM Evals that Do & Don't Work Evals for classification, summarization, translation, copyright regurgitation, and toxicity. | #3400:00 达到 | 00:00首次采集时已在榜 | —结束时仍在榜 | 7小时37分累计在榜 | 1无重入 |
35 Don't Mock Machine Learning Models In Unit Tests How unit testing machine learning code differs from typical software practices | #3500:00 达到 | 00:00首次采集时已在榜 | —结束时仍在榜 | 7小时37分累计在榜 | 1无重入 |
36 How to Generate and Use Synthetic Data for Finetuning Overcoming the bottleneck of human annotations in instruction-tuning, preference-tuning, and pretraining. | #3600:00 达到 | 00:00首次采集时已在榜 | —结束时仍在榜 | 7小时37分累计在榜 | 1无重入 |
37 Language Modeling Reading List (to Start Your Paper Club) Some fundamental papers and a one-sentence summary for each; start your own paper club! | #3700:00 达到 | 00:00首次采集时已在榜 | —结束时仍在榜 | 7小时37分累计在榜 | 1无重入 |
38 2023 Year in Review An expanded charter, lots of writing and speaking, and finally learning to snowboard. | #3800:00 达到 | 00:00首次采集时已在榜 | —结束时仍在榜 | 7小时37分累计在榜 | 1无重入 |
39 Push Notifications: What to Push, What Not to Push, and How Often Sending helpful & engaging pushes, filtering annoying pushes, and finding the frequency sweet spot. | #3900:00 达到 | 00:00首次采集时已在榜 | —结束时仍在榜 | 7小时37分累计在榜 | 1无重入 |
40 Out-of-Domain Finetuning to Bootstrap Hallucination Detection How to use open-source, permissive-use data and collect less labeled samples for our tasks. | #4000:00 达到 | 00:00首次采集时已在榜 | —结束时仍在榜 | 7小时37分累计在榜 | 1无重入 |
41 Reflections on AI Engineer Summit 2023 The biggest deployment challenges, backward compatibility, multi-modality, and SF work ethic. | #4100:00 达到 | 00:00首次采集时已在榜 | —结束时仍在榜 | 7小时37分累计在榜 | 1无重入 |
42 AI Engineer 2023 Keynote - Building Blocks for LLM Systems Evals, retrieval-augmented generation, guardrails, and collecting feedback; all that good stuff. | #4200:00 达到 | 00:00首次采集时已在榜 | —结束时仍在榜 | 7小时37分累计在榜 | 1无重入 |
43 Evaluation & Hallucination Detection for Abstractive Summaries Reference, context, and preference-based metrics, self-consistency, and catching hallucinations. | #4300:00 达到 | 00:00首次采集时已在榜 | —结束时仍在榜 | 7小时37分累计在榜 | 1无重入 |
44 How to Match LLM Patterns to Problems Distinguishing problems with external vs. internal LLMs, and data vs non-data patterns | #4400:00 达到 | 00:00首次采集时已在榜 | —结束时仍在榜 | 7小时37分累计在榜 | 1无重入 |
45 Patterns for Building LLM-based Systems & Products Evals, RAG, fine-tuning, caching, guardrails, defensive UX, and collecting user feedback. | #4500:00 达到 | 00:00首次采集时已在榜 | —结束时仍在榜 | 7小时37分累计在榜 | 1无重入 |
46 Obsidian-Copilot: An Assistant for Writing & Reflecting Writing drafts via retrieval-augmented generation. Also reflecting on the week's journal entries. | #4600:00 达到 | 00:00首次采集时已在榜 | —结束时仍在榜 | 7小时37分累计在榜 | 1无重入 |
47 Some Intuition on Attention and the Transformer What's the big deal, intuition on query-key-value vectors, multiple heads, multiple layers, and more. | #4700:00 达到 | 00:00首次采集时已在榜 | —结束时仍在榜 | 7小时37分累计在榜 | 1无重入 |
48 Open-LLMs - A list of LLMs for Commercial Use It started with a question that had no clear answer, and led to eight PRs from the community. | #4800:00 达到 | 00:00首次采集时已在榜 | —结束时仍在榜 | 7小时37分累计在榜 | 1无重入 |
49 Interacting with LLMs with Minimal Chat Should chat be the main UX for LLMs? I don't think so and believe we can do better. | #4900:00 达到 | 00:00首次采集时已在榜 | —结束时仍在榜 | 7小时37分累计在榜 | 1无重入 |
50 More Design Patterns For Machine Learning Systems 9 patterns including HITL, hard mining, reframing, cascade, data flywheel, business rules layer, and more. | #5000:00 达到 | 00:00首次采集时已在榜 | —结束时仍在榜 | 7小时37分累计在榜 | 1无重入 |