elanning

Joined 6 years ago

Karma

104

Submissions

Member since

Jul 1

View on Hacker News

Recent submissions

Comment · 7 days ago

> I think Astra was trained on neural weights data as an attempt by OpenAI to get to recursive self improvement.

This might be the case, a few weeks ago, I wanted to compare a small neural network trained with AdamW vs a handcrafted set of weights on a random task. Astra was able to handcraft a set of weights that perfectly fit the small neural network to the task. AdamW was unable to tune the weights to get the same result.

I believe we've known humans can handcraft weights much more efficiently than standard gradient descent methods, we just don't have enough memory or time to scale ourselves, so it makes sense to train a neural network to do it on our behalf. I am excited to see how far we can push this method.

Mentioned chat: https://chatgpt.com/share/6ae8f024-34ec-83e8-9572-1300f52c80...

Comment · 1 year ago

I wrote a minimal implementation of this feedback loop here:

https://github.com/Ichigo-Labs/p90-cli

But if you’re looking for something robust and production ready, I think installing Claude Code with npm is your best bet. It’s one line to install it and then you plug in your login creds.

Comment · 1 year ago

It looks great, nice work. I’m impressed at the quick development too.

Comment · 1 year ago

I know the feeling. I like to picture it as a kitchen, and those “bat-whatever” gadgets are like those silly infomercial cooking tools that are only good for one specific thing. Meanwhile the good abstractions are like a nice knife, that can be used in so many different contexts.

Comment · 2 years ago

Big mistake on my part; I should clarify I fine-tuned both PaddleOCR and TrOCR on large amounts of data specific to my domain. I cannot speak on the best out of the box “ready to go” solutions (besides cloud ones, which were quite good with the right pre and post processing).

Comment · 2 years ago

I’ve done a lot of OCR work and tesseract is nearly a decade out of date at this point. It is not a serious technology for anything requiring good accuracy or minor complexity. From what I’ve seen, GPT-4V completely smokes tesseract, but then again, most modern OCR systems do. If you want fast and pretty powerful OCR, check out paddle. If you want slower but higher accuracy, check out transformer based models such as TrOCR.

Comment · 2 years ago

I’ve been having a good time using REST level 0.5

https://faithlife.codes/blog/2023/09/rest-level-zero-dot-fiv...

Comment · 2 years ago

Also plugging my related project: https://github.com/Ichigo-Labs/cgrep From the comments in this thread, it seems a lot of people have built or needed an easy way to quickly create static analysis checks, without a bunch of hassle. I think extended regex is a great way to do this.

Comment · 4 years ago

Rest in peace to one of the greats.

You might want to consider reading The Design of Design if you liked The Mythical Man-Month.

Comment · 4 years ago

Wow this could be incredibly useful for a lot of applications. I’m excited to see the new wave of tools this could spawn.

Comment · 4 years ago

This looks like a nice piece of work. I hope the author continues on it, or other fun hobby projects.

Comment · 4 years ago

This looks like a nice piece of work. This area and adjacent tooling areas are ripe for improvement.

Comment · 4 years ago

I review Posthog PRs occasionally. In addition to this, they’re also open source. Seems like a cool place.

Comment · 4 years ago

This is typically a good way to organize React projects, in my experience. A few top-level components which hold state with a useReducer and have a few functions to make backend calls, as needed. You could consider the reducer the model and the top-level component the controller. All components that sit below the top-level are pure view components. Props in, view out. They at most hold a minor amount of UI state. They don’t make API calls or update state themselves, that must be done with a callback to the top-level component.

This makes testing simple as you can test the reducer without rendering any UI. The pure view components are also easy to test. Then a few end to end tests to tie everything together.

https://www.reactguide.dev/#mc-v-trees Has more info on how to scale the pattern for larger apps.