Miju Labs

← All buyers · Sierra

K

Karthik Narasimhan

Head of Research · Sierra

high confidenceTier B · Map and watchApp-layer post-trainerstext

Recent posts

When we first conceptualized SWE-bench in the summer of 2023, the driving question was "What do software engineers really do and how do we measure LLMs on those tasks?" (this was back when HumanEval was the standard coding benchmark, testing models on simply code generation) Fast forward to now and both the models and the SWE role have leveled up significantly -- software engineers now spend a lot more time on understanding requirements, tasteful design and validating solutions than writing actual code. And Senior SWE-bench is designed to push those limits even further by testing modern SWE agents on tackling such underspecified problems and evaluating them for both correctness and taste. Be sure to read @henryehrenberg 's excellent blog articles (senior-swe-bench.snorkel.ai/blog) on the various design choices as well as an analysis of the first round of results!
314455.7KView on X ↗
@princeton_nlp graduated 11 (!) PhDs at the hooding ceremony yesterday. Their research has fundamentally shaped the global AI landscape in so many ways, and they have been a core part of building the NLP group and its collegial spirit. It's been a real privilege working with and getting to know them all over the past few years! @ZexuanZhong @AmeetDeshpande_ @SadhikaMalladi @_carlosejimenez @JensTuyls @VishvakM @__howardchen @xiamengzhou @gaotianyu1350 @danfriedman0 @_awettig w/ @danqi_chen @prfsanjeevarora
72218927KView on X ↗
Deep work and deep thinking will be increasingly valuable in a world where AI agents automate a lot of knowledge work. Spawning tens of agents in parallel and context switching between them feels productive, but it's mostly dopamine.

Why they are on the map

Sierra author page: 'Head of Research at Sierra'; τ-bench lead source — evidence dated 2025-03

Shapes what 'good data' means.

How Sierra buys data

Publishes τ-bench, τ²-bench and Hyper-τ-Bench agent benchmarks (2024–26). Hired 'Product Manager, Agent Data Platform' (Aug 2025). No human-data vendors publicly named.

Small research team led by Karthik Narasimhan (also Princeton faculty) owns benchmarks/evals.

Full dossier pending

This person was mapped in pass 1. Career, what they have said on the record, interviews, connections, why they matter to us and how to reach them are added in pass 2.