jakedahn

Ooo, yeah!

I’m excited to play with their memory stuff. I’m curious if they will add any hooks for allowing skills to store things intentionally.

The system skill idea is a little different in that you can store and query structured data out of your own SQLite db.

Author here-- hah, I'm surprised someone posted this already-- I just came to share it as a Show HN post and get the conversation started:

I’ve been playing with Claude Skills and stumbled on a simple pattern for tiny, durable personal data systems:

* CLI: a small, self-contained executable

* SKILL.md: the operator's manual (what to run, how to parse output, how to think about the system)

* SQLite: a local DB for persistent state

It’s nothing mind-blowing, but the ergonomics of this combo feel great.

If you define a process/flow, Claude can "turn the crank" by running the CLI, accumulating context, and animating the system to life over time.

They’re also easy to share: you can distribute System Skills via Claude Code’s `/plugin marketplace add <repo>`.

More details in the blog post and the toy Pomodoro System Skill reference implementation here:

Blog: https://www.shruggingface.com/blog/the-system-skill-pattern Repo: https://github.com/jakedahn/pomodoro

--

Curious whether any of this resonates. Also excited to hear any interesting System Skill ideas worth exploring!

what API are you using for recipes?

hi friends!

I'm the author of t2x and shrugginface.com, I'm surprised to see this landed on HN a month after I first shared it.

I originally planned to make it real during the holiday break but got distracted by other projects. This is the inspiration bump I needed, so I'll get back to shipping over the coming weeks

Simon's LLM tool is probably the best of any of these sorts of things! So thank you for making it, I still use it regularly to kick the tires on new models, and it served as a significant inspiration for the design of t2x.

The idea behind t2x was to make a stripped-down cli with a "functionality first" mindset and remove the actual selection of specific models from the user's flow.

If you run `ls -la | t2x "sort these files alphabetically"`, it will do the right thing.

However, subcommand like `t2x ask` are used to route you to a different model with different behavior. The ask subcommand currently makes requests to perplexity, where you can ask questions and get near realtime grounding from the world.

I'm curious, what specifically you're interested in from openrouter? Do they offer specific LLMs, or is it just a great way to kick the tires on new models as they emerge?

The original intention behind t2x was to be "functionality first", and make an opinionated call on which LLMs get used for specific functionality. However I think the way to go will be sane defaults and then allow user-specified models from something like openrouter.

oooo neat! I hadn't heard of aichat before, I'll definitely take a look.

I made this as a silly learning project to dive into some of the real-time interestingness of Elixir.

It's using Phoenix LiveView, and the whole game state lives inside a GenServer

Realtime state is written to ETS and periodically (every 5s) flushed to disk.

It's running on fly.io

---

code lives on github here: https://github.com/jakedahn/clickthebutton/blob/main/lib/cli...

and https://github.com/jakedahn/clickthebutton/blob/main/lib/cli...

ooo, that could be fun! Like an in-browser tldraw mspaint UI , good idea!

Has anyone done this analysis for other llms like llama2?

Thank you for making this!

I have a 1.5yo that’s obsessed with pointing out planes in the sky.

Now we can go plane watching together!

It has merged! https://github.com/ggerganov/llama.cpp/pull/1773

I haven't had a chance to try it yet, but I am :excitedllama:

https://www.shruggingface.com/

I started this blog a few months ago to explore the emerging world of generative AI. Hoping to write much more soon!

I built it as a next.js app with mdx support, and the microblog posts are rendered from a custom notion CMS setup.

ah-ha! This was probably it

Thank you for these recommendations! I'll definitely be trying them next time 'round.

Mostly because I thought of it more as an art project than a technical accuracy project. However, the honest answer to your question, is because I have a ridiculous amount of photos of my dog on my phone . Getting training data is hard work.

But this is totally true, I found that maybe 30% of the images I generated did not look like my dog at all. However the rest do a good job at capturing his eyes and facial expressions that he actually makes. I thought that the chosen image I worked from captured the look of his eyes super well.

But yeah, nobody but me would really appreciate that.

hah, these are pretty cool! Well done!

Yeah, it was likely just user error. I actually really love Draw Things, because I can run it locally on my mac and quickly experiment without having to sling HTTP requests or spin up GPUs.

I did the actual work back on March 11th, so I was likely on an older build; but I was seeing issues where inpainting was just replacing my selection/mask with a white background. I had the inpainting model loaded, but couldn't figure it out.

I'm planning to continue playing with Draw Things locally, and exploring the inpainting stuff. For such an iterative process I feel like a local client would make for the best experience.

Yeah!

Here's the colab notebook, in case anyone is interested: https://github.com/TheLastBen/fast-stable-diffusion

I've trained a few smaller models using their Dreambooth notebook, but I think for 4000 training steps, an A100 will usually take 30-40min. I believe replicate also uses A100s for their dreambooth training jobs.

These are great!

https://fast.ai is hands down the best resource for learning more about deep learning as a normal software person.

rbates, if you're reading this, thank you!

I learned so much from railscasts in my early software engineering journey. Your videos took me from copy-pasta extraordinaire to actually understanding how to build complex features and wire things together.

I wouldn't be where I am today without you.

Also noteworthy: for me it feels like any time a "side project" turns into a "side hustle" -- the ideas usually fizzle out very quickly.

Sometimes it's worth remembering that side projects can be "just for fun", and it's okay if you're going to spend a few dollars on it. The value can come from the learning process, and creative input/output generated.

One brainhack I like to use on myself is to think of them as "Side Quests!" rather than "Side Projects."

My main quest is my day-to-day life. When I'm feeling bored, bogged down, and tired of the daily grind -- I head out in search of a side quest.

A side quest can be easy (1 hour), or hard (14 days). But the goal of a side quest is to distract me from my daily grind, and help keep me learning and motivated.

While this difference in perspective is subtle, I feel like it's enough to give me the headspace to stay more deeply engaged with interesting topics I'm trying to learn or understand.

I wrote a related blog post last week on related thoughts, if you're interested: https://jakedahn.com/2020/06/23/its-not-a-side-project-its-a...

ship weekly!

I just finished up the first version of a side project I have been working on and I'm looking for any feedback, please let me know if you have any positive or critical thoughts :)

I just finished up the first version of a side project I have been working on and I'm looking for any feedback, please let me know if you have any positive or critical thoughts :)

I just finished up the first version of a side project I have been working on and I'm looking for any feedback, please let me know if you have any positive or critical thoughts :)

Have you seen pytest-xdist? I use pytest-xdist to achieve the same type of workflow for any python project. You can do `py.test -f foo/bar_tests.py`, and every time you hit save it will rerun all of the tests, if one fails it will "focus" on the failed test so every time you hit save it will only rerun the failing tests.