GuaxiCast

Why does almost every interface built with AI look the same? In this episode, we put Claude to the test: one coffee app spec, four runs, and two design skills to see if anything breaks the generic "AI-made" look.

Check the results in: https://lfomendes.medium.com/can-design-skills-make-claude-look-less-like-claude-f535bc1fb1d4

Luiz Felipe Mendes built Coffee Nerds, a journal for home coffee brewers, four times with the same project file and the same model (Claude Opus 5.5):

- Default: no skill, just "execute this"

- Claude Design: no skill, using Claude's design feature

- Taste Skill: a skill focused on bold, intentional UI

- UI UX Pro Max: a broader design guide for web and mobile

What we cover:

- Why AI-generated interfaces converge on the same buttons, cards, fonts and layouts

- How much Claude Design alone changes the result (spoiler: less than you'd expect)

- How UI UX Pro Max adds personality while staying inside familiar app conventions

- Why Taste Skill was the only one to truly break the pattern, while still delivering every feature in the spec

- The bigger lesson: the spec decides the structure, the skill decides the look

- Limitations of the test, and when a human designer is still the best choice

Read the full post with screenshots of every version: [Medium link]

Try it yourself: the project spec and every version are on GitHub, one branch per design: https://github.com/lfomendes/guaxinim-tests

Built by Luiz with AI:

- iWish, event pages with invitations, RSVP and gift lists: https://iwish.gifts

- Guaxí, shifts and payments for doctors: https://guaxi-app.com.br

This episode was generated with Google NotebookLM from the original Medium post.

https://lfomendes.medium.com/can-design-skills-make-claude-look-less-like-claude-f535bc1fb1d4

Ever wonder why your Netflix home screen looks different from your friends'? In this episode, we dive into the fascinating evolution of how Netflix selects the perfect cover art to get you to click "Play."

We trace a decade of innovation: from the early days of simple A/B testing in 2016, to the creation of AVA in 2018—a sophisticated tool that uses face detection and cinematography principles like the "rule of thirds" to find high-quality frames—and finally to the cutting-edge use of Causal Machine Learning in 2023.

We explore how Netflix moves beyond mere correlation to understand the actual "cause and effect" of user engagement, all while keeping human artists and specialists in the loop to ensure quality and creativity.

Original Source: Transforming Data into Art: The Evolution of Cover Selection at Netflix

The Professional Focus (Deep Dive) Is AI just a hype cycle, or is it the greatest shift in human productivity? In this episode, we dive into the workflows of top AI researchers and engineers. Drawing from the experiences of Nicholas Carlini (Google DeepMind) and Luiz Felipe Mendes (ML Engineer), we move past the marketing magic to look at real-world use cases. Discover how these experts use LLMs like Gemini and ChatGPT to build web apps from scratch, convert complex codebases to Rust, and automate the monotonous tasks that slow down every professional.

In this episode, we explore the reality of taking machine learning out of the classroom and into the real world. While many believe that modeling is the core of AI, it is often the smallest and sometimes the "easiest" component of a successful system. We break down the complete, iterative workflow required for industry success—from Project Setup and Data Pipelines to Modeling and Serving.

Drawing on insights from Luiz Felipe Mendes and the work of Chip Huyen, we discuss why simplicity is a superpower, how strong baselines can outperform complex deep learning models, and why you should spend more time cleaning data than chasing the latest hype. We also tackle the critical "forgotten" aspects of ML, including model interpretability, handling algorithmic bias, and navigating privacy concerns. Whether you are preparing for a machine learning interview or building your first production application, this episode provides the foundational best practices every practitioner needs to know

Episode Overview

In this episode, we dive into the insights of data scientist and entrepreneur Luiz Felipe Mendes as he explores the shifting landscape of Artificial Intelligence. We move beyond simple LLM prompts to discuss the rise of AI Agents—autonomous programs that don't just talk but act. We also tackle the critical need for ML Prediction Robustness, examining why large-scale systems like those at Meta and iFood require more than just good engineering to stay reliable.

Key Discussion Points

• Defining the AI Agent: Understanding how agents differ from standard chatbots by using external APIs and iterative loops to achieve complex goals.
• Agentic Workflows: A look at Andrew Ng’s theories on "agentic workflows," where AI systems use feedback loops—such as one agent writing code while another tests it—to improve quality autonomously.
• The "Reality Check" on Autonomy: A candid discussion on the current limitations of agents, including their struggles with long-term task tracking, limited context windows, and the ongoing necessity of human supervision.
• The Pillar of Robustness: Why technically "functional" models can still fail in production due to the stochastic nature of data.
• Engineering for Reliability: A breakdown of Meta’s approach to robustness, focusing on four critical areas:
  • Model & Feature Robustness: Detecting anomalies (like a car priced at 10 reais) before they break a system.
  • Label & Prediction Robustness: Ensuring distributions remain consistent over time.
  • ML Interpretability: Using tools like SHAP values to peer inside the "black box" of complex models.

Major Takeaways

• Iterative vs. Direct: The power of AI today lies in "agentic" workflows that allow for self-correction.
• Constant Vigilance: ML systems are core components of modern products and require continuous monitoring of features, labels, and predictions to remain robust.

Resources Mentioned

• Luiz Felipe Mendes’ "Weekly Readings" series.
• Andrew Ng’s lecture on AI Agentic Workflows.
• MIT Technology Review: "What are AI agents?".
• Meta’s engineering blog on ML prediction robustness.

This podcast was generated based on these show posts

https://lfomendes.medium.com/weekly-reading-ai-agents-8414e387bfd8

https://lfomendes.medium.com/weekly-reading-metas-approach-to-machine-learning-prediction-robustness-fae46957cf41

Netflix's documentary Coded Bias argues that machine-learning systems quietly absorb the sexism and racism of the society that builds them — and that facial recognition in the hands of governments and big tech raises serious privacy stakes. In this episode, drawn from Luiz Felipe Mendes' 2021 essay (updated for the GPT era), we walk through what the film gets right, where it oversimplifies, and why "the technology isn't evil — how we deploy it is" is the throughline. We also connect the film's warnings to today's large language models.

In this episode:

• Why AI isn't inherently evil, and how the same models that encode bias can be used to detect and reduce it
• The film's strengths: human stories, concrete real-world examples, and that it actually proposes solutions (regulation, not just alarm)
• Where it falls short: treating algorithms as sinister "entities," and the overstated "black box" framing
• Transparency vs. global interpretability vs. local interpretation — and the tools that make models explainable
• Regulation in practice: Brazil's LGPD and Europe's GDPR
• A 2023 update: how GPT-4, Bard, and other LLMs inherit the very biases the documentary warned about

Resources mentioned:

• Documentary: Coded Bias (2021)
• Bolukbasi et al., "Man Is to Computer Programmer as Woman Is to Homemaker?" — arxiv.org/abs/1607.06520
• "A Survey on Bias and Fairness in Machine Learning" — arxiv.org/abs/1908.09635
• Explainability tools: LIME (github.com/marcotcr/lime), SHAP (github.com/slundberg/shap), Shapash (maif.github.io/shapash)
• Christoph Molnar, Interpretable Machine Learning — christophm.github.io/interpretable-ml-book

Read the original post on Medium: medium.com/@lfomendes

GuaxiCast turns Luiz Felipe Mendes' essays on AI, data science, and building in public into short, honest conversations. Built with curiosity, shipped with ☕.