Matt Sims

Teach Claude Code to think systematically. I got tired of having the same conversation with Claude Code. Review this for security. Are these tests sufficient? Can you find patterns in my codebase and update the instruction files? The answers were ok but inconsistent: no clear methodology, no memory between sessions, no systematic depth. So I built one Claude Code plugin, then another. Before I knew it I had five, covering instruction files, test coverage, security, codebase analysis, and code evolution. I decided to merge them into one integrated plugin. Claude universe was available so I figured why not… The Claude Universe plugin: teach Claude Code to think systematically Github link (entirely open source): github.com/mbwsims/claude… More at claudeuniverse.com

@pbakaus Wow, this looks very awesome

Design inside your codebase. Introducing Impeccable 3.0: ▸ 1 skill, self-contained, 23 commands ▸ /impeccable live: pick in-browser, get prod-grade variants, accept writes to *source* ▸ reads+writes DESIGN.md + PRODUCT.md ▸ brand & product design impeccable.style

It took 8 years from this post (thanks to some major advancements in LLMs) for this to become easy to implement. But the bigger takeaway is that there's a ton of theoretical concepts in computing and technology from the last century that are now almost effortless to build. We should all be doing a better job of reading those archives. They're full of some pretty incredible ideas.

Matt recently showed me what he’s been tinkering on behind closed doors and he started to build in the open and I was impressed! Very excited to see his projects drop, many at the intersection of creativity, storytelling and AI. You should def give him a follow if you’re into narrative storytelling (he’s got an interesting background - English PhD *and* ML/startup background)

@PeterHollens Break it and then open a PR!

@mbwsims MY DUDE!!!! LET'S CHAT SOON! WOULD LOVE TO BREAK YOUR STUFF! ;) haha i'll text ya

Teach Claude Code to think systematically. I got tired of having the same conversation with Claude Code. Review this for security. Are these tests sufficient? Can you find patterns in my codebase and update the instruction files? The answers were ok but inconsistent: no clear methodology, no memory between sessions, no systematic depth. So I built one Claude Code plugin, then another. Before I knew it I had five, covering instruction files, test coverage, security, codebase analysis, and code evolution. I decided to merge them into one integrated plugin. Claude universe was available so I figured why not… The Claude Universe plugin: teach Claude Code to think systematically Github link (entirely open source): github.com/mbwsims/claude… More at claudeuniverse.com

Introducing Impeccable 2.0. • data-driven skill rewrite (evals across 7 niches) → better font/color diversity • /critique: subagent de-bias + deterministic anti-pattern detection • visual mode: /critique, CLI, (soon) Chrome • npx impeccable detect (files + URLs) Demo:

Some valuable research on LLMs, fiction writing, and how to measure creativity: "One of the main contributions of our work is the collection of 14 tests, referred to as the Torrance Test for Creative Writing (TTCW), to evaluate creativity in short fictional stories."

We were wondering: can we build a good instruction LLaMa W/O relying on large amounts of human annotations or distillation from other models? We found a scalable recipe where the model itself can be put in the loop of generating and curating finetuning data to further self-train

New @GoogleAI paper! 📜 Language models repeat a user’s opinion, even when that opinion is wrong. This is more prevalent in instruction-tuned and larger models. Finetuning with simple synthetic-data (github.com/google/sycopha…) reduces this behavior. arxiv.org/abs/2308.03958 1/

Highly recommend submitting to the AI Song Contest. This was our submission from 2021: soundcloud.com/user-703675253…

New working paper quantifying arXiv publication patterns in the age of LLMs! Joint work with @rajivmovva, @sidhikab1, @kennylpeng, @gsagostini, and @NikhGarg. We analyze LLM citation patterns, fastest growing topics, many other things. Some of our findings: 1/N

Llama 2 is out! ai.meta.com/llama This new version has better language generation, more layers of safety, a broad set of partners – and a license that authorizes commercial use. I continue to believe that an open approach is the right path to build better models!

Animate-A-Story is a video storytelling approach which can synthesize high-quality, structured, and character driven videos. Composition and scene transitions are still early days, but interesting to see how a first text-to-story pipeline looks like. videocrafter.github.io/Animate-A-Story

@davecraige for sure

@RoyPrice For sure - if you send me a DM with your email I'll add you to the closed beta.

@mbwsims I’d love to try it

It will improve but I think people worry too much about AI writing screenplays. Bigger opportunity in analyzing story, helping writers outline and in finding facts. In writing, I see it becoming a tool more than anything else.

We released a big update to the @sudowrite Summarize function - it now generates loglines along with a more coherent summary of the plot Here's its take on my short story In the Space of Twelve Minutes uncannymagazine.com/article/in-the… Reply with a story and I'll run it!

@Ted_Underwood Yeah, one of the authors' arguments is that the strict left-to-right generation of autoregressive LMs is a strong limiting factor for complex controllable generation tasks, a shortcoming that the denoising process of diffusion models effectively avoids