AI is the biggest change to UX design in 60 years, yet we know embarrassingly little about how people actually use it. Here are 76 open research questions, organized into 7 lists sized for everyone from high school students to the big AI labs. Students who complete a research challenge gain the two qualities employers now screen for: agency and demonstrated AI experience.

Agent Skill for systematic UX writing — scale content quality through AI-powered design system enforcement. Works with Claude and Codex. - content-designer/ux-writing-skill

Design systems solve visual consistency, but content quality still depends on individual writers. Every error message, button label, and empty state requires manual review to ensure it's clear, concise, conversational, and purposeful. This doesn't scale.

The open-source engine to organize your Twitter bookmarks with AI

Siftly connects to your Twitter/X account (with your permission, of course), fetches your bookmarks, and processes them through an AI model. It doesn't just list them; it analyzes the content and intelligently groups tweets into meaningful categories like "Web Development," "Startup Advice," "Python Libraries," or "Industry News." The end result is a clean, organized view of your saved content that you can actually browse and use, transforming a chaotic list into a structured knowledge base.

https://github.com/viperrcrypto/Siftly

A course by Andrej Karpathy on building neural networks, from scratch, in code.
We start with the basics of backpropagation and build up to modern deep neural networks, like GPT. In my opinion language models are an excellent place to learn deep learning, even if your intention is to eventually go to other areas like computer vision because most of what you learn will be immediately transferable. This is why we dive into and focus on languade models.
Prerequisites: solid programming (Python), intro-level math (e.g. derivative, gaussian).

July 12, 2017

As a Software Development Manager, I have a devil of a time trying to find experienced Software Developers, so the post got me thinking. How can there be this tech talent drought, while the number of remote developers offering their services online continues to grow?

"The hard part isn't the technology — the number one failure of the software industry is building the wrong product."

"The most valuable asset in the software industry is the synthesis of programming skill and deep context in the business problem domain, in one skull."

Not so much. At the outset, a business problem might appear simple, or only somewhat complex. You might think you have a handle on all the caveats and corner cases. But the average person who hasn't programmed extensively doesn't appreciate the level of detail and explicitness that computers require to do absolutely anything. Every behavior must be dictated with excruciating specificity. And your plan for how users will interact with the system will likely get thrown out and redrawn from scratch dozens of times before you have a minimum viable product.

Most of the time is spent thinking and communicating about a virtually endless number of micro-problems that seemingly emerge out of nowhere, and constitute the real territory between the technology and the business problem. Part of traversing this landscape of micro-problems is inventing, communicating, and internalizing a plethora of named and unnamed abstractions. It is the only way to break down the complexity so you can grapple with it.

AI-powered design platform for creating beautiful interfaces and experiences

https://docs.superdesign.dev/quickstart

This blog post is very long and almost entirely about the 1974 bestseller Zen and the Art of Motorcycle Maintenance by Robert M. Pirsig. It is also about AI—there will be some juicy takes, pinky swear—but those familiar with ZAMM should consider themselves warned.

Fabric is an open-source framework for augmenting humans using AI. It provides a modular system for solving specific problems using a crowdsourced set of AI prompts that can be used anywhere. - danielmiessler/Fabric

https://www.opensourceprojects.dev/post/e548ac30-a0c6-4396-b81e-892568966088

AI pair programmers are powerful but not magical – they have no prior knowledge of your specific project or intent beyond what you tell them or include as context. The more information you provide, the better the output. We’ll distill key prompt patterns, repeatable frameworks, and memorable examples that have resonated with developers. You’ll see side-by-side comparisons of good vs. bad prompts with actual AI responses, along with commentary to understand why one succeeds where the other falters. Here’s a cheat sheet to get started:

A roundup of the command-line tools and terminal setups shared at the 2026 edition of our now-annual CLI throwdown at the Perl Toolchain Summit.

• eza
• superpowers
• fastgron
• fx
• dyff

The <(...) syntax runs a command and presents its output as if it were a file (pipe), which lets you feed command output to programs that expect a filename.

# See how the contents of two directories differ
diff <(ls dir-one) <(ls dir-two)

https://www.olafalders.com/2025/06/03/the-great-pts-cli-throwdown/

• yazi
• tailscale
• neovim plugins
• bat
• typos
• shutter (linux)

Other tools

• ncdu - ncdu (NCurses Disk Usage) is an interactive, text-based disk space analyzer.

I'm Jesse. I make stuff. Software, hardware. Very occasionally, trouble.

https://simonwillison.net/2025/Oct/10/superpowers/

Gemini CLI Tips and Tricks. Contribute to addyosmani/gemini-cli-tips development by creating an account on GitHub.

https://news.ycombinator.com/item?id=46060508

1. The Professional Email Writer

“Act as a senior communication specialist. Rewrite this email to sound professional, clear, concise, and polite while keeping my original intent. Improve tone, structure, grammar, and flow. My email: [paste email].”

3. The Corporate Reply

“Craft a professional reply to this email I received: [paste email]. Maintain a respectful tone, address all points clearly, and write a response that strengthens trust and communication.”

Other prompts:
https://www.theailibrary.co/prompts

Think First

Most people assume that with Claude Code and other AI tools, the first thing you need to do is type (or start talking). But that's probably one of the biggest mistakes that you can make straight off the bat. The first thing that you actually need to do is think.

Have a deep back and forth with ChatGPT/Gemini/Claude, where you describe exactly what you want to build, you ask the LLM for the various options you can take in terms of system design, and ultimately the two of you settle on a solution. You and the LLM should be asking each other questions, not just a one way street.

Before you ask Claude to build a feature, think about the architecture. Before you ask it to refactor something, think about what the end state should look like. Before you ask it to debug, think about what you actually know about the problem. The more information that you have in plan mode, the better your output is actually going to be because the better the input is going to be.

Keep it short.

Claude can only reliably follow around 150 to 200 instructions at a time, and Claude Code's system prompt already uses about 50 of those.

Tell it why, not just what. Claude is a little bit like a human in this way. When you give it the reason behind an instruction, Claude implements it better than if you just tell it what to do.

Update it constantly.

Press the # key while you're working and Claude will add instructions to your CLAUDE.md automatically.

Use external memory.

If you're working on something complex, have Claude write plans and progress to actual files (I use SCRATCHPAD.md or plan.md). These persist across sessions. When you come back tomorrow, Claude can read the file and pick up where you left off instead of starting from zero.

When Claude Gets Stuck

Simplify the task

1. An overview of agents

2. How the capability of an AI-powered agent is determined by the set of tools it has access to and its capability for planning

3. How to select the best set of tools for your agent

4. Whether LLMs can plan and how to augment a model’s capability for planning

5. Agent’s failure modes

AI-powered agents are an emerging field with no established theoretical frameworks for defining, developing, and evaluating them. This post is a best-effort attempt to build a framework from the existing literature, but it will evolve as the field does.

Lots of good replies, some that say he is FOS. Others point out that these might be too restrictive for everyday tasks.

The more interesting part for me (esp as a computer vision at heart who is temporarily masquerading as a natural language person) is whether pixels are better inputs to LLMs than text. Whether text tokens are wasteful and just terrible, at the input.

Maybe it makes more sense that all inputs to LLMs should only ever be images. Even if you happen to have pure text input, maybe you'd prefer to render it and then feed that in.

I dislike the tokenizer. Tokenizers are ugly, separate, not end-to-end stage. It "imports" all the ugliness of Unicode, byte encodings, it inherits a lot of historical baggage, security/jailbreak risk (e.g. continuation bytes). It makes two characters that look identical to the eye look as two completely different tokens internally in the network. A smiling emoji looks like a weird token, not an... actual smiling face, pixels and all, and all the transfer learning that brings along. The tokenizer must go.

https://github.com/deepseek-ai/DeepSeek-OCR

My preferred definition of an LLM agent is something that runs tools in a loop to achieve a goal. The art of using them well is to carefully design the tools and loop for them to use.

• The joy of YOLO mode
• Picking the right tools for the loop
• Issuing tightly scoped credentials
• When to design an agentic loop
• This is still a very fresh area

AI coding agents take the shortest path to done, which usually means skipping the specs, tests, and reviews that make software reliable at scale. Agent Skill...

https://x.com/datachaz/status/2040357775830814798?s=43&t=gAZhA3-2h2DvLb-eSzGa5A

https://github.com/addyosmani/agent-skills

@addyosmani
from Google just dropped his new Agent Skills and it's incredible.

It brings 19 engineering skills + 7 commands to AI coding agents, all inspired by Google best practices 🤯

AI coding agents are powerful, but left alone, they take shortcuts.

They skip specs, tests, and security reviews, optimizing for "done" over "correct." Addy built this to fix that.

Each skill encodes the workflows and quality gates that senior engineers actually use: spec before code, test before merge, measure before optimize.

The full lifecycle is covered:

→ Define - refine ideas, write specs before a single line of code
→ Plan - decompose into small, verifiable tasks
→ Build - incremental implementation, context engineering, clean API design
→ Verify - TDD, browser testing with DevTools, systematic debugging
→ Review - code quality, security hardening, performance optimization
→ Ship - git workflow, CI/CD, ADRs, pre-launch checklists

Features 7 slash commands: (/spec, /plan, /build, /test, /review, /code-simplify, /ship) that map to this lifecycle.

https://news.ycombinator.com/item?id=45652952

According to the DeepSeek paper, you can pull out 10 text tokens from a single image token with near-100% accuracy. In other words, a model’s internal representation of an image is ten times as efficient as its internal representation of text. Does this mean that models shouldn’t consume text at all? When I paste a few paragraphs into ChatGPT, would it be more efficient to convert that into an image of text before sending it to the model? Can we supply 10x or 20x more data to a model at inference time by supplying it as an image of text instead of text itself?