ChatGPT is shockingly bad at poker I’m impressed by large language models. So why can't they get the basics of poker right?
Does Field Ordering Affect Model Performance? I mostly wrote this post as an excuse to try the freshly-minted and excellent pydantic-evals framework for LLM evaluations but one intere...
Why Use Bayesian Methods for A/B Testing | Briefer Why Bayesian methods can be more interesting and intuitive than frequentist ones when it comes to A/B testing.
Decoder-Only Transformers are SoTA Encoders (with some fine-tuning) Decoder-only transformer architectures have taken over. Encoder-based transformer (encoder-only, encode-decode) architectures (e.g. BERT) are becoming something of the past, the latest encoder-based transformer was released ~2 years ago. Large research la...
ChatGPT Heard About Eagles Fans Your gender, ethnicity, and fandom can invisibly influence Your chatbot
Death by a 1000 standups Here’s why I hate standup meetings: they’re a colossal waste of time. Worse, they feel like work (and so no one complains).
My Tony Robbins Experience When I was a kid, my sister came home with a book she claimed could give you superpowers. People said that after reading it, they could levitate. I had no idea what that meant, but I was sold. The boo
Let’s Flip an Unfair Coin Flipping a coin is a universal way to quickly solve small disagreements between two parties. E.g. you want pizza and I want Mexican, so let’s just flip a coin.
MCP seems viral The Model Context Protocol, its rate of adoption, nature, and implications, seem viral in nature.
on instagram addiction i was addicted to instagram for about a month. it upended my life enough that i realized that i was living with something new-an undesirable habit. and once i realized this, it seemed like it would be wise to try to address it or at least think about it. ...
Inertial Rails project setup to use code generated from v0 (ShadcnUI, TailwindCSS4, React, TypeScript) and deploy with Kamal I’ve never been great at CSS or front-end styling, so I lean on frameworks to pick up the slack. Back in the day, Bootstrap plus a good theme was all I needed. ...
GitHub wants to spam open source projects with AI slop the dead GitHub theory Text version: https://pivot-to-ai.com/2025/05/20/github-wants-to-spam-open-source-projects-with-ai-slop/ Please send money! It’s very helpful! Patreon: https://www.patreon.com/davidgerard Ko-Fi: https://ko-fi.com/A1529D5 Buy me nic...
By Default, Signal Doesn't Recall Signal Desktop now includes support for a new “Screen security” setting that is designed to help prevent your own computer from capturing screenshots of your Signal chats on Windows. This setting is automatically enabled by default in Signal Desktop on Wi...
AI and Vector Data Extensions are now Generally Available (GA) - .NET Blog We’re excited to announce that these extensions are now generally available, providing developers with a robust foundation to build scalable, maintainable, and interoperable AI-powered applications.
Expire vs Remove. Which should we use in Fusion Cache? Expire vs Remove. Which should we use in Fusion Cache? Fusion Cache quickly became my favorite caching library for C#. Can't live without it! In this video, we go over some of the basic cache operations we have access to. Watch the full tutorial here: ...
Master The Basics of MSTest Like a PRO In Under 15 minutes! For centuries one testing framework has dominated the donet scene... but is it all over for xUnit?! In this video, we'll explore MSTest and how some of the great Microsoft Testing Platform capabilities have made their way in. Is it enough to get you to ...
Which ABP Template Should You Use? In this snippet from our Community Talks, we compare ABP's single-layer, layered, and microservice templates to help you decide which one best fits your project needs. Full video: https://www.youtube.com/live/bqsxaBIrcsQ?si=oCu5ikYZ3YCf8mk2 Our website: ...
My new hobby: watching AI slowly drive Microsoft employees insane Jokes aside, GitHub/Microsoft recently announced the public preview for their [GitHub Copilot...
Announcing Gemma 3n preview: powerful, efficient, mobile-first AI- Google Developers Blog Introducing Gemma 3n – the latest Google open model for accessible AI, featuring unique flexibility, privacy, and expanded multimodal capabilities on mobile devices.
Introducing Google AI Ultra: The best of Google AI in one subscription Learn about Google AI Ultra, Google’s new AI subscription with the highest access to our most capable models and premium features.