Tessera
Folgen

Eugene Yan

@eugeneyan.com

RecSys, AI, Engineering; Principal Applied Scientist @ Amazon. Led ML @ Alibaba, Lazada, Healthtech Series A. Writing @ eugeneyan.com, aiteratelabs.com.

455 Posts10811 Follower331 Folgt
Eugene Yan@eugeneyan.com · 11mo ago

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

Eugene Yan@eugeneyan.com · last yr.

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.

Eugene Yan@eugeneyan.com · last yr.

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
Eugene Yan@eugeneyan.com · last yr.

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.

Eugene Yan@eugeneyan.com · last yr.

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.

Eugene Vinitsky 🍒@eugenevinitsky.bsky.social · last yr.

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

Eugene Yan@eugeneyan.com · last yr.

Product evals are misunderstood. Many teams think that adding another tool, metric, or llm-as-judge will solve all their problems and save their product. But that just dodges the hard truth and avoids the real work. Here's how to fix your process instead. eugeneyan.com/writing/eval...

An LLM‑as‑Judge Won't Save Your Product—Fixing Your Process Will

Applying the scientific method, building via eval-driven development, and monitoring AI output.

eugeneyan.com

Eugene Yan@eugeneyan.com · last yr.

Interesting paper from Google that challenges a core assumption in translation evaluation—a single metric can measure both accuracy & naturalness. They found that the best systems had neural metrics that did not correlate with human preferences. arxiv.org/abs/2503.24013

You Cannot Feed Two Birds with One Score: the Accuracy-Naturalness Tradeoff in Translation

The goal of translation, be it by human or by machine, is, given some text in a source language, to produce text in a target language that simultaneously 1) preserves the meaning of the source text an...

arxiv.org

Eugene Yan@eugeneyan.com · last yr.

Had a session with very senior folks on how they build with AI and can’t help thinking there’s no better time to learn, clarify, brainstorm, write, debate, plan, design, code, debug, review, analyze, delegate, play, and in general do more more while doing less with AI—so psyched!

Eugene Yan@eugeneyan.com · last yr.

@hamel.bsky.social & his wisdom on evals, error analysis, looking at your data is what we need. Here are his 10 Don'ts: • Don't skip error analysis • Don't skip looking at your data • Don't gatekeep who can write prompts • Don't let zero users be a roadblock • Don't be blindsided by criteria drift

Eugene Yan@eugeneyan.com · last yr.

Great example of generate -> validate loop + error analysis > "the most effective route to improve outcomes was brute force: retry steps until they passed or reached a limit. We give the validation errors ... to the LLM and built a loop runner"

airbnb generate-validate loop
Eugene Yan@eugeneyan.com · last yr.

Stumbled on the first(?) RAG in NarrativeQA from 2017. Because books & movies were too large for LSTMs to do Q&A on, they embedded 200-word chunks and retrieved similar snippets to answer questions. "Chunking and cosine similarity retrieval is so 2017." arxiv.org/abs/1712.07040

4.3 Neural Benchmarks on Stories The design of the NarrativeQA dataset makes the straight-forward application of the existing neural architectures computationally infeasible, as this would require running an recurrent neural network on sequences of hundreds of thousands of time steps or computing a distribution over the entire input for attention, as is common. We split the task into two steps: first, we retrieve a small number of relevant passages from the story using an IR system, and subsequently, apply one ofthe neural models above on the resulting document. The question becomes the query for retrieval. This IR problem is much harder that traditional document retrieval, as the documents, the passages here, are very similar, and the question is short and entities mentioned likely occur many times in the story. Our retrieval system considers chunks of 200 words from story and computes representations for all chunks and the query. We then select a varying number of such chunks based on their similarity to the query. We experiment with different representations and similarity measures in Section 5. Finally, we concatenate the selected chunks in the correct temporal order and insert delimiters between them to obtain a much shorter document. For span prediction models, we then further select a span from the retrieved chunks as described in Section 4.2.
Eugene Yan@eugeneyan.com · last yr.

What are your favorite resources on translating long documents with LLMs? Generating -> validating -> regenerating translations, etc. Also, identifying defects where gender pronouns, formality, idioms, etc are mistranslated, such as for Spanish, German, etc. Please share! 🙏