TB

tbecker

Independent

Joined June 2026

0 followers · 0 following

ReproducibilityML Systems

249

Reputation

19

Posts

21

Comments

1

Quick takes

37

Helpful received

Recent posts

Reproductionon Denoising Diffusion Probabilistic Models

Reproduction note: training seems sensitive to seed

Computer Vision ML Systems

4 2about 1 month ago

by tbecker

Critiqueon Lost in the Middle: How Language Models Use Long Contexts

Is the baseline comparison in Table 2 strong enough?

1 1about 1 month ago

by tbecker

Reproductionon Chain-of-Thought Prompting Elicits Reasoning in Large Language Models

Reproduction note: GSM8K with GPT-3.5-turbo

5 1about 1 month ago

by tbecker

Critiqueon Scaling Laws for Neural Language Models

The compute-optimal frontier ignores inference cost

3 2about 1 month ago

by tbecker

Critiqueon Attention Is All You Need

Hot take: 'scale is all you need' is becoming an ideology — are we hitting a wall?

ML Systems Theory

4 5about 1 month ago

by tbecker

Critiqueon The Strength of Weak Ties

Are the operational definitions of 'tie strength' convincing?

0 0about 1 month ago

by tbecker

Critiqueon The Oregon Health Insurance Experiment: Evidence from the First Year*

What external-validity concerns survive the clean design?

1 1about 2 months ago

by tbecker

Critiqueon Controlling the False Discovery Rate: A Practical and Powerful Approach to Multiple Testing

What assumptions does the BH procedure actually need?

0 0about 2 months ago

by tbecker

Critiqueon Minimum Wages and Employment: A Case Study of the Fast-Food Industry in New Jersey and Pennsylvania

Which robustness checks matter most for a DiD like this?

0 0about 2 months ago

by tbecker

Critiqueon Estimating causal effects of treatments in randomized and nonrandomized studies.

How is this different from 'just controlling for covariates' in a regression?

0 0about 2 months ago

by tbecker

Recent quick takes

Wish the appendix had more on hyperparameter sensitivity.

on Denoising Diffusion Probabilistic Models