billylo

Add them to the on-call schedule.

I ran a comparison using this OPF with what I have in clarity.evergreen-labs.org (it's a Tauri app with local PII redaction.)

A few things jump out:

1) Dates are aggressively redacted, creating false positives. 2) Non-English names are not working yet.

love this. thanks for sharing!

Thank you. The learning aspect of reading how AI tackles something is rewarding.

It also reduces my hesitation to get started with something I don't know the answer well enough yet. Time 'wasted' on vibe-coding felt less painful than time 'wasted' on heads-down manual coding down a rabbit hole.

I upgraded from M3 Air to M5 Pro 14". Not for LLM, but for faster build times. The disk access time is much faster on M5 Pro. My build time (iOS/Android) was reduced by more than 50%. So, that alone is worth the upgrade.

This will foster multi-app collaboration.

Google devs: Please consider doing this on Firebase to make it work on iOS and web too.

Great idea. Addresses a real need. Best of luck with your launch!

Thank you! This is brilliant. I have it bookmarked.

Thank you for your service.

I use my spare time helping kids at a FIRST robotics team. It's fun.

The technical strategy is sound. However, I anticipate major mobile apps will add MCP capabilities to their app very soon too, making less use of intents going forward.

Hope this helps.

Thanks for a great write-up!

Production-quality software can now be made in weeks (instead of months and quarters.) I anticipate an exciting period of fast innovation in all industries, supported by lots of good product-engineers with different levels of experience. The areas I am the most excited about is healthcare (as we live longer) and sustainability. It will be fun to be a part of.

It's real struggle. Nations will not likely put the brakes on because of its need for self defence. I ponder your question too.

Inception

This is fun. Thank you!

Time it takes to go from 100m users to 5 billions: Internet (25 years), Smartphone (13), AI? (tracking to achieve that in ~6 years!)

https://evergreen-labs.org/assets/Acceleration.jpg

We learned computer languages so we can ask computers to do work for us. It was out of necessity because there are no other ways.

If we can instruct computers with natural language 50% of the time, that's 50% less translation work for our human brains. I have no problem with not needing to write instructions in computer languages (no regex, no sed/awk, no python even) for day-to-day stuff.

Critical thinking, reasoning are another story. We can't let those skills atropied.

We should ask how the traders manage this. It's essentially 24/7 markets in the world. For them, the FOMO effects are even stronger... actual money earning opportunity.

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.

https://learn.microsoft.com/en-us/windows/ai/apis/phi-silica

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.