billylo

I wonder how best we can measure the usefulness of models going forward.

Thumbs up or down? (could be useful for trends) Usage growth from the same user over time? (as an approximation) Tone of user responses? (Don't do this... this is the wrong path... etc.)

That's why benchmarks are useful. We all suffer from the shortcomings of human perception.

xcode has been getting better bit-by-bit. No major regression.

Each distro is doing their own thing. If you are targeting Linux mainly, I would suggest to code it on top of ollama or LiteLLM

Windows and macOS does come with a small model for generating text completion. You can write a wrapper for your own TUI to access them platform agnostically.

For consistent LLM behaviour, you can use ollama api with your model of choice to generate. https://docs.ollama.com/api/generate

Chrome has a built-in Gemini Nano too. But there isn't an official way to use it outside chrome yet.

Please let us know when and which LLM changes its "minds". This is a cool experiment. I wish there are more time-bound datasets that we can experiment with to get a better sense on how LLMs are influenced.

I did a fact check on the article and it seems to check out. I am happy to help billy@evergreen-labs.org.

I'd also suggest to reach out to the author of the NYT article and look for ideas. They took the time to study the subject and will likely have some insights on what could work (tech or non-tech approaches.)

Same here. Agents has allowed me to take on more experiments because the cost for testing ideas is now much much lower.

Compared to moving to assembly coding to high level languages, which change do you think is more dramatic? I am curious.

If you are curious about doing something similar with TPU, Google has an article. https://developers.googleblog.com/train-gpt2-model-with-jax-...

FIFA world cup has been selling opportunities for Right-to-buy. Monopolistic behavior.

Mid 50s software maker. Transitioned from slashdot.org. Why? It's frequented by fellow builders and a good place to learn from others. (higher signal vs noise ratio than other places.)

The exact opposite: AI has made the mundane go away, so I can focus on the differentiating features.

1. I spend less time fiddling with Flutter/SwiftUI to make things look decent. 2. I don't have to worry about simple data management code much. 3. I learn new things much faster by watching AI does its thing.

Beautiful and useful at the same time. Love it.

Thank you. Will try it today.

Great idea. And host them on github-next-2025.com or maybe use it as a new benchmark to see how models/tools progress.

I'm retired and write apps as community givebacks and as a creative outlet.

No, I am not sad because I am in control. If there is something I want to take on as an intellectual challenge, I do it.

If it's just mechanical tasks or UI layout tweaking, AI is perfect. I can become the user who keeps asking for fine-tuning of corner radius. :-)

I added a Practice Mode in my speech-to-speech translator app 3PO. It allows you to practise talking with chatGPT and gets assessment score on your accuracy.

Topic is preset. (chatGPT plays the role of a travel guide to help you find places to go in Holland (for Dutch))

https://3po.evergreen-labs.org

Installed and test-driven it...

Really like the fact that it's easy to start doing something useful. I may end up using it for some screen scraping too. Puppeteer is powerful, but the scripts tends to be brittle.

Keep up the good work!

A 3D-printed part + two washers + battery case. DIY approach. https://www.printables.com/model/383741-cr2032-battery-adapt...

Perfect. Thanks!

Love it! I seriously want to use it as a background for my server.

(any chance to publish a version with a configurable speed?)

Fairly basic there... chunking audio (websocket) and send them for translation sequentially.

The tech is really here. This summer, I was fascinated the accuracy by the spoken language auto-detection capabilities. It really works and it only needs 1-2 seconds to catch the nuiance of a specific language.

So, I ventured into building 3PO. https://3po.evergreen-labs.org

Would love to hear everyone's feedback here.

thanks for the kind words!! It is built on top of a fairly straightforward infrastructure. Client side is C#, .NET, MAUI. Server side is Firebase Cloud Functions/Firestore/Web Hosting + Azure.

No problem! Some fixes were on the server side. We had a server side issue a couple days ago for a few hours. You may have been affected by it, giving you those errors. They have been fixed too. Take care!

Author of 3PO here: check out our latest version 2.12. Many fixes have been incorporated in the past two weeks. Cheers.

I use codeium.com - chose it mainly because it has solid plugins for Xcode and VS Code.

Pricing link: https://skip.tools/pricing/