hbcondo714

> a burst of incoming traffic can share warm environments instead of mapping each request to a new one

But cold starts could still occur, especially in a low-traffic environment where requests come in seldomly?

When a file is uploaded, we will make a best-effort attempt in your browser to remove any private details using Rampart[1]

[1] https://america.gov/privacy-policy

I just remembered I created a website via Solo when it was released a couple years ago: https://soloist.ai/amarkota

Please note the Reviews are auto-generated

Taking a quick look at the network traffic, the site does a POST to https://america.gov/api/chat with a JSON payload when submitting a query:

  {"language":"en","id":"VSvMeyCMKTX05oLW","messages":[{"parts":[{"type":"text","text":"how do I register my new business?"}],"id":"oHub5UDJ3iYARhao","role":"user"}],"trigger":"submit-message"} 

So the user's query is hitting a server so to answer my own question, the answer is No to local inference / models.

Edit: PDF attachments and voice input are processed locally according to the site's privacy policy[1]. But they still use 3rd party 'AI Providers' that abide by a ZDR.

[1] https://america.gov/privacy-policy

> Your personal information isn’t collected or stored, and your conversation disappears when you leave.

I am left to wonder how this is technically accomplished. Is inference running in the browser? Is the model downloaded to the user’s machine?

Thanks, we've been using firecracker VMs with AWS MicroVM[1] and Fly.io Sprites[1] but interested in using Workers instead

[1] https://news.ycombinator.com/item?id=48642510

[2] https://news.ycombinator.com/item?id=46557825

That is a nice sequence diagram[1]; I like how each endpoint param values are written out and the color distinctions. What tool did you use to create it?

[1] https://storage.ghost.io/c/b8/53/b853e3d4-3186-409d-9c7f-7da...

> Hosting companies can change...Point your domain somewhere else when you need to move. That is a much healthier relationship with technology.

I went from Azure to Github for hosting so I guess my relationship with Microsoft ended up staying the same?

[1] https://amarkota-com-www.azurewebsites.net

[2] https://github.com/hbcondo/hbcondo

Our tenants live in our property that is in a known Airport Influence Area ("AIA")[1] but this year, they reported to us the noise associated with the airport's Instrument Approach Procedures have increased. Airplanes arriving at the airport fly less than 1,000 feet in elevation right above our neighborhood. Even worse, airplanes come in consecutively so the noise is back to back w/o much reprieve.

The Noise and Capacity Office allows to manually report[2] such aircraft but I'm wondering if this device can detect these aircrafts which can lead to report submission. Any insight on doing this is appreciated!

[1] https://lacounty.maps.arcgis.com/home/item.html?id=7cb3fb165...

[2] https://viewpoint.emsbk.com/lgb7

@SubiculumCode, thanks for this comment and helping us understand better. Is there by chance a way to contact you about your research & expertise or would you mind contacting me using my profile info? I built https://behavior.today and would love to connect on this topic. Thanks!

I was gifted an Oura 4 last year and thought it accurately tracked my sleep. But a couple months ago, the sleep debt metric went flat to 0 even when I tagged poor nights of sleep (mainly due to child care).

Some discussion here:

Citadel Buys Situational Awareness's Stock Portfolio After Big Losses in AI

https://news.ycombinator.com/item?id=49111879

More precisely, 23 new positions were reported in their latest filing just a couple months ago, most of those being semiconductors:

https://last10k.com/sec-filings/2045724

> You are an elite frontend engineer and design-to-code specialist. The design image is the primary source of truth; your code is the translation layer. Do not reinterpret or "improve" the design into something generic — reproduce it faithfully.

Thank you for sharing this. I was just using OpenAI's Product Design plugin[1] to create designs but it just didn't reproduce it in code faithfully so will need to try this.

[1] https://openai.com/business/plugins/product-design/

Maybe try Ollama Cloud, Prompt or response data is never logged or trained on:

https://ollama.com/pricing

I’ve been using the Observable Framework[1] for this kind of work but it doesn’t appear to be actively developed anymore so will look into Datasette.

[1] https://github.com/observablehq/framework

Is there by chance a way to password protect the generated site?

> LLMs and VLMs, Running Inside OpenCV…Qwen 2.5, Gemma 3, PaliGemma, and the GPT-2 / GPT-4 family

Why these specific models / versions?

This article is from a couple weeks ago, the same day ADT submitted "Other Information" to the SEC about unauthorized access:

https://www.sec.gov/Archives/edgar/data/1703056/000170305626...

Not to be picky but the careers page is saying Live in production. 10M+ SEC filings

https://jobs.ashbyhq.com/kepler-ai

I just wanted to learn more about the company but reside in California and open roles are in New York