HNHacker News
TopNewBestAskShowJobs

billylo

275 karma · joined October 17, 2014

maker at evergreen-labs.org
submissionscomments
billylo··on The Future of Software Engineering Isn't What You Think
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.

billylo··on AI Is a Lethal Threat This Year
It's real struggle. Nations will not likely put the brakes on because of its need for self defence. I ponder your question too.
billylo··on My smart sleep mask broadcasts users' brainwaves to an open MQTT broker
Inception
billylo··on Show HN: Terminalcore – The Rhythm Game for PC
This is fun. Thank you!
billylo··on Tell HN: AI is not a slippery slope, it's a waterslide
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

billylo··on Tell HN: AI is not a slippery slope, it's a waterslide
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.

billylo··on AI fatigue is real and nobody talks about it
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.
billylo··on Claude Code daily benchmarks for degradation tracking
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.)

billylo··on Claude Code daily benchmarks for degradation tracking
That's why benchmarks are useful. We all suffer from the shortcomings of human perception.
billylo··on The struggle of resizing windows on macOS Tahoe
xcode has been getting better bit-by-bit. No major regression.
billylo··on Ask HN: What's a standard way for apps to request text completion as a service?
https://learn.microsoft.com/en-us/windows/ai/apis/phi-silica
billylo··on Ask HN: What's a standard way for apps to request text completion as a service?
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
billylo··on Ask HN: What's a standard way for apps to request text completion as a service?
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.

billylo··on Every LLM hallucinates that std:vector deletes elements in LIFO order
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.
billylo··on Ask HN: Should I start a software foundation (goal: help emergency services)?
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.)

billylo··on AI Code assistants has made completing side projects so easy
Same here. Agents has allowed me to take on more experiments because the cost for testing ideas is now much much lower.
billylo··on Cursor and Claude Opus 4.5 is a game changer
Compared to moving to assembly coding to high level languages, which change do you think is more dramatic? I am curious.
billylo··on LLM from scratch, part 28 – training a base model from scratch on an RTX 3090
If you are curious about doing something similar with TPU, Google has an article. https://developers.googleblog.com/train-gpt2-model-with-jax-...
billylo··on Internal emails reveal Ticketmaster helped scalpers jack up prices, FTC says
FIFA world cup has been selling opportunities for Right-to-buy. Monopolistic behavior.
billylo··on Out of curiosity: what kind of people use this "forum" (I mean Hacker News)?
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.)
billylo··on Ask HN: Did modern AI's coding abilities make you lose interest in programming?
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.

billylo··on Show HN: Sping – An HTTP/TCP latency tool that's easy on the eye
Beautiful and useful at the same time. Love it.
billylo··on We put a coding agent in a while loop
Thank you. Will try it today.
billylo··on We put a coding agent in a while loop
Great idea. And host them on github-next-2025.com or maybe use it as a new benchmark to see how models/tools progress.
billylo··on Ask HN: Are developers sad about AI writing more of their code?
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. :-)

billylo··on Ask HN: Conversational AI to Learn a Language
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

billylo··on Maestro – Next generation mobile UI automation
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!

billylo··on A 10-Year Battery for AirTag
A 3D-printed part + two washers + battery case. DIY approach. https://www.printables.com/model/383741-cr2032-battery-adapt...
billylo··on The Bluesky firehose viewed in the style of a Windows XP screensaver
Perfect. Thanks!
billylo··on The Bluesky firehose viewed in the style of a Windows XP screensaver
Love it! I seriously want to use it as a background for my server.

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

← PreviousPage 2 of 7Next →