Shawn Simister

Building AI powered tools to augment human creativity and problem solving. Previously @GitHub and @Google 🇨🇦

[Shawn Simister @narphorium]

I've been thinking about why verifying AI agent output feels so much harder than writing the spec that produced it. That question led me to rethink where my attention actually belongs in the process, and eventually to build https://t.co/TpxaTqqqag https://t.co/UBbhJaFkFH

[Ethan Mollick @emollick]

Big paper on AI coding agents using Github & other data

The auto-complete tools (Copilot) led to 2.2x more code, local agents like original Claude Code led to 7.4x, & current remote coding agents 17.3x(!)

But human bottlenecks in coding means actual releases "only" went up 30%

[Shawn Simister @narphorium]

@tanishqk I've been thinking about this as well. But I've found that agents aren't great at divergent thinking. Without human guidance they revert to the safest, most generic options. In my experience, the human input has the most leverage at the beginning of each diamond.

[Shawn Simister @narphorium]

@sh_reya I'm building something similar! It started as a way to write code but now I use it for everything https://t.co/OxePMcpXrX

[Shawn Simister @narphorium]

This is how I use AI to augment my design process. Instead of having the agent show me a giant diff of changes, Atelier links each edit back to the original thread of feedback so I can review them in context

[Shawn Simister @narphorium]

@boristane I’m working towards this with Atelier https://t.co/UBbhJaEMQ9

[Omar Khattab @lateinteraction]

your novel idea, when you ask an llm to fill in the details

[Shawn Simister @narphorium]

@Westoncb @mrtudl I suspect the RL training loop rewards solving the task in as few steps as possible and that discourages the agent from searching for additional constraints

[Shawn Simister @narphorium]

@Westoncb @mrtudl Also hedge your questions. Instead of just "should I refactor this to a shared lib?" add "... or would that make it too strongly coupled?" so it has to weigh both sides

[Jeremy Howard @jeremyphoward]

We desperately need better ways of evaluating models. Something that shows how helpful they are at working hand-in-hand with humans to help them get stuff done in a cooperative/iterative way.

The Claude models have consistently been better at this, and the market rewards that.

[Shawn Simister @narphorium]

@RidgetopAI You should also check out https://t.co/TRppmLvPwJ from @IanArawjo for inspiration

[Shawn Simister @narphorium]

@Westoncb This was my first attempt at it last year: https://t.co/QFwaPkVQDz but I've been thinking a lot about it since then and I'm hoping to come back to that problem again

[Shawn Simister @narphorium]

@Westoncb Totally agree. Deliberately delegating parts of the task to parallel subagents is a really powerful technique. I wrote up some similar ideas here: https://t.co/XBxiYRzBx0

[Shawn Simister @narphorium]

@nbaschez Looks like we're working towards the same goal https://t.co/OxePMcqvhv

[Shawn Simister @narphorium]

This is how I use AI to augment my design process. Instead of having the agent show me a giant diff of changes, Atelier links each edit back to the original thread of feedback so I can review them in context

[Chuanyang Jin @chuanyang_jin]

What are users thinking during their interactions with LLMs?

We introduce ThoughtTrace — the first large-scale dataset that captures what users think during real-world human–AI conversations, not just what they type.
→ 10,174 thought annotations
→ 2,155 multi-turn conversations, 17,058 turns
→ 1,058 users
→ 20 LLMs

These thoughts improve user behavior prediction (+41.7%) and model alignment (+25.6%).
This opens a new paradigm of user-centric LLM research. Full information in the thread 🧶

Read our paper: https://t.co/lRYJvGJ7bb
Check our project website: https://t.co/AupCn1YQOk

[Shawn Simister @narphorium]

@CasJam This is how I do it https://t.co/OxePMcqvhv

[Shawn Simister @narphorium]

This is how I use AI to augment my design process. Instead of having the agent show me a giant diff of changes, Atelier links each edit back to the original thread of feedback so I can review them in context

[Shawn Simister @narphorium]

@HamelHusain Wow. Is that an html report as the terminal state or do you ever feed the html back into other prompts as context?

[Shawn Simister @narphorium]

@dearmadisonblue A new kind of REPL but instead of everything being a list everything is Markdown

[Shawn Simister @narphorium]

@lucasmeijer I think of it like Tetris vs Sudoku: https://t.co/bHNXR6YpVp

[Jaimz @Jaimz_with_a_Z]

I always found it hard to document large codebases in a way that made sense to me visually

Thanks to @tldraw I built CodeCanvas, my own infinite canvas documentation tool for mapping out my thought process

Excited to share some of my favorite features

[Shawn Simister @narphorium]

@jason_mayes That's how I use my Creator Micro. Just get @work_louder to create custom keys for you

[Shawn Simister @narphorium]

@threepointone Remember when C++ compilers cost $500 and Visual Studio was over $1000?