Lightnews — Scholar-powered news

Reposted by Eugene Yan

Ethan @ethanrosenthal.com · 23d

I’ve seen semantic IDs pop up but never bothered to actually look into them. This write up from @eugeneyan.com is a great intro that also illustrates why they’re pretty interesting for mixing recsys and LLMs eugeneyan.com/writing/sema...

How to Train 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.

eugeneyan.com

1 6

Eugene Yan @eugeneyan.com · 24d

yeap the plan is to map products to semantic IDs which the model can understand

1 3

Eugene Yan @eugeneyan.com · 24d

code for data prep, training the RQ-VAE, SASRec, Qwen3-8B, chatting with the model, etc

github.com/eugeneyan/se...

GitHub - eugeneyan/semantic-ids-llm: Semantic IDs: How to train an LLM-Recommender Hybrid with steerability and reasoning on recommendations.

Semantic IDs: How to train an LLM-Recommender Hybrid with steerability and reasoning on recommendations. - eugeneyan/semantic-ids-llm

github.com

3

Eugene Yan @eugeneyan.com · 24d

demo of the LLM-recommender hybrid returning both semantic IDs & english, and:
• steering recs via natural language
• explaining the recommendation
• naming the bundle of recommendations
• multi-turn conversation to get recs

watch till the end for the bloopers lol

www.youtube.com/watch?v=_0n4...

LLM-Recomender Hybrid with Steerable Recommendations and Reasoning on Recommendations

YouTube video by Eugene Yan

www.youtube.com

1 2

Eugene Yan @eugeneyan.com · 24d

For example, given a sequence of items, it can recommend the next best item. But better than that, you can steer the recommendations with natural language! And it can explain why it gave that recommendation, as well as creatively name recommendation bundles.

1

Eugene Yan @eugeneyan.com · 24d

I've been nerdsniped by the idea of Semantic IDs.

Here's the result of my training runs:
• RQ-VAE to compress item embeddings into tokens
• SASRec to predict the next item (i.e., 4-tokens) exactly
• Qwen3-8B that can return recs and natural language!

eugeneyan.com/writing/sema...

How to Train 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.

eugeneyan.com

2 6 25

Reposted by Eugene Yan

Eugene Yan @eugeneyan.com · Jun 25

Wrote an intro to evals for long-context Q&A systems:
• How it differs from basic Q&A
• What dimensions & metrics to eval on
• How to build llm-evaluators
• How to build eval datasets
• Benchmarks: narratives, technical docs, multi-docs

eugeneyan.com/writing/qa-e...

Evaluating Long-Context Question & Answer Systems

Evaluation metrics, how to build eval datasets, eval methodology, and a review of several benchmarks.

eugeneyan.com

3 15

Eugene Yan @eugeneyan.com · Jun 25

Wrote an intro to evals for long-context Q&A systems:
• How it differs from basic Q&A
• What dimensions & metrics to eval on
• How to build llm-evaluators
• How to build eval datasets
• Benchmarks: narratives, technical docs, multi-docs

eugeneyan.com/writing/qa-e...

Evaluating Long-Context Question & Answer Systems

Evaluation metrics, how to build eval datasets, eval methodology, and a review of several benchmarks.

eugeneyan.com

3 15

Eugene Yan @eugeneyan.com · May 21

Some thoughts on leadership: eugeneyan.com/writing/lead...
• What makes an exceptional leader?
• What do exceptional leaders do?
• Leadership styles: Commando, soldier, police

1 9

Eugene Yan @eugeneyan.com · May 20

For example, Amazon started to implement the first version of Amazon Prime in late 2004 and announced it on February 2 2005, six weeks later. An account of how it came amount and lots of anecdotes here. vox.com/recode/2019/...

Also this list: patrickcollison.com/fast

The making of Amazon Prime, the internet’s most successful and devastating membership program

An oral history of the subscription service that changed online shopping forever.

vox.com

2

Eugene Yan @eugeneyan.com · May 20

The best leaders I’ve worked with operate with perma-urgency. They act like early founders, mindful of existential threats. And they can balance speed, sustainability, and repay tech debt. Ultimately, customers love it and teams thrive when we ship fast to deliver delight.

1 7

Eugene Yan @eugeneyan.com · May 18

converted all images to webp and hopefully made the site faster. something i wouldn't have bothered in the past

✅ selfcheckgpt.jpg: 226.15KB → 60.53KB (73.24% reduction)
✅ query-processing.jpg: 95.74KB → 42.84KB (55.25% reduction)
✅ sldc-specialists.jpg: 30.88KB → 12.37KB (59.95% reduction)
✅ feature-store-ad.png: 157.24KB → 57.73KB (63.29% reduction)
✅ llm-patterns-aieng-2023-v0-004.jpg: 132.81KB → 43.50KB (67.24% reduction)
✅ google-user-intent.png: 46.67KB → 24.80KB (46.86% reduction)
✅ quy-nguyen.jpeg: 4.27KB → 1.98KB (53.61% reduction)
✅ fbi-tab2.jpg: 396.10KB → 128.28KB (67.61% reduction)
✅ ey-fastball.png: 4.94KB → 0.46KB (90.71% reduction)
✅ favicon-16x16.png: 0.60KB → 0.26KB (56.96% reduction)
✅ android-chrome-192x192.png: 11.50KB → 2.96KB (74.30% reduction)
✅ apple-touch-icon.png: 10.15KB → 2.55KB (74.88% reduction)
✅ android-chrome-512x512.png: 33.22KB → 6.72KB (79.77% reduction)
✅ favicon-32x32.png: 1.35KB → 0.45KB (66.45% reduction)
✅ 404-8.jpg: 43.90KB → 21.81KB (50.32% reduction)
✅ 404-9.jpg: 42.80KB → 16.86KB (60.60% reduction)
✅ 404.jpg: 25.67KB → 6.37KB (75.20% reduction)
✅ 404-11.jpg: 91.48KB → 13.71KB (85.02% reduction)
✅ 404-10.jpg: 309.60KB → 34.35KB (88.91% reduction)
✅ 404-12.jpg: 68.38KB → 50.75KB (25.79% reduction)
✅ 404-13.jpg: 73.79KB → 38.56KB (47.74% reduction)
✅ 404-14.jpg: 86.34KB → 45.91KB (46.82% reduction)
✅ 404-1.jpg: 25.67KB → 6.37KB (75.20% reduction)
✅ 404-2.jpg: 113.98KB → 67.45KB (40.82% reduction)
✅ 404-3.jpg: 38.06KB → 13.68KB (64.04% reduction)
✅ 404-7.jpg: 55.02KB → 26.54KB (51.77% reduction)
✅ 404-6.jpg: 45.98KB → 15.45KB (66.41% reduction)
✅ 404-4.jpg: 94.63KB → 50.33KB (46.82% reduction)
✅ 404-5.jpg: 48.97KB → 17.69KB (63.87% reduction)

==================================================
SUMMARY STATISTICS
==================================================
Total files converted: 1002
Total original size: 122.78MB
Total WebP size: 38.75MB
Total size reduction: 84.03MB (68.44%)
Average size reduction per file: 68.44%
Proportional savings: 122.78MB → 38.75MB
==================================================

3

Eugene Yan @eugeneyan.com · May 18

Previously, these tasks weren't worth the effort but now they can be done in hours. What an amazing time to build and play =D

1 4

Eugene Yan @eugeneyan.com · May 18

Had a fun couple of hours this weekend with Codex & Windsurf
• Migrated off deprecated jekyll-algolia to official sdk (better indexing)
• Added recommendations + relevance scores to each post
• Improved site responsiveness; fixed dark mode flicker
• Marie Kondo-ed unused files & dead code

Image of recommender widget at the bottom of posts on eugeneyan.com

1 1 5

Eugene Yan @eugeneyan.com · May 14

In orgs pushing the envelope, there's always a minority that can be counted on to get shit done against all odds, driven by force of will, resourcefulness, influence, etc. When you identify them, vest in them authority, autonomy, and step back and watch them perform miracles.

1 5

Eugene Yan @eugeneyan.com · May 7

opps! thanks for letting me know, fixed!

3

Eugene Yan @eugeneyan.com · May 7

p.s., If you’re interested in topics like this, my friends Ben and Swyx are organizing the AI Engineer World’s Fair in San Francisco on 3rd - 5th June. Come talk to builders deploying AI systems in production. Here’s a big discount for tickets: ti.to/software-3/a...

AI Engineer World's Fair 2025

The AI Engineer World's Fair is the biggest technical AI event of the year, happening Summer 2025, the one place you can meet with ~every major AI lab from OpenAI to Anthropic to Cohere, every AI infr...

ti.to

1

Eugene Yan @eugeneyan.com · May 7

Here's the code for the mcp-server (src), prompts (context), and generated summaries from May 4th (summaries).

github.com/eugeneyan/ne...

GitHub - eugeneyan/news-agents: Building News Agents to Summarize News with MCP, Q, and tmux

Building News Agents to Summarize News with MCP, Q, and tmux - eugeneyan/news-agents

github.com

1 1

Eugene Yan @eugeneyan.com · May 7

Here's a three-minute demo of news-agents in action. It's pretty cool at the 30-second mark how the sub-agents get spawned! We then see the main agent assigning tasks and polling for progress, and finally shutting the sub-agents down when they're done with their assigned tasks.

1 3

Eugene Yan @eugeneyan.com · May 7

To better understand MCPs and agentic workflows, I built news-agents to generate a daily news recap. The main agent spawns sub-agents, assigning them news feeds to parse and summarize, and then generates a final overall summary plus analysis.

eugeneyan.com/writing/news...

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.

eugeneyan.com

4 4 22

Eugene Yan @eugeneyan.com · Apr 30

@hamel.bsky.social & @sh-reya.bsky.social are two of the world's best on evals. They've built evals for 35+ AI apps & helped teams ship confidently. Now they'll teach everything they know on building evals that work.

Enrollment closes in 4 days.

Secret 35% discount code: maven.com/parlance-lab...

2 4

Eugene Yan @eugeneyan.com · Apr 27

The Art of Doing Science and Engineering: Learning to Learn by Richard Hamming only $1.99 for the Kindle version today: amazon.com/dp/B088TMLQDC

8

Reposted by Eugene Yan

Harrison Pim @harrisonpim.com · Apr 26

Enjoyed this on eval-driven product development from @eugeneyan.com. It chimes with my own experiences building around LLMs and search engines, including the thoughts on automated evaluators.
When deconstructed, EDD is just the good old scientific method under a new name

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.

eugeneyan.com

2 7

Eugene Yan @eugeneyan.com · Apr 26

Surround yourself with people whose "work" is their calling, craft, and play.

They are intrinsically motivated, are driven to excel and do what's right, and and get so much shit done just because it's fun.

13

Reposted by Eugene Yan

Eugene Vinitsky 🍒 @eugenevinitsky.bsky.social · Apr 26

Some of the anti-AI stuff feels a bit like when people would say "don't use Wikipedia as a source." It's just like anything else, a piece of information that you weigh against multiple sources and your own understanding of its likely failure modes

580 39 460