Hacker News: ammario

New comment by ammario in "An update on residential proxies and the scraper situation"

ammario — Sat, 11 Jul 2026 04:47:37 +0000

There are PoW approaches that even the playing field between data centers and desktops. RandomX is my favorite.

New comment by ammario in "The hallucinogenic mushroom that contains no known psychedelic"

ammario — Mon, 15 Jun 2026 04:16:24 +0000

Similar phenomena consistently reported in high doses of Benadryl: little spiders.

New comment by ammario in "Electricity use of AI coding agents"

ammario — Wed, 21 Jan 2026 15:04:52 +0000

Lol, this is my PR. That cost is misleading. That workspace did far more than that change. In reality I spend ~$1000/week in tokens for all of my development work, and I'm quite happy with the exchange.

New comment by ammario in "A desktop app for isolated, parallel agentic development"

ammario — Mon, 24 Nov 2025 16:24:45 +0000

Curious to hear more.. why is random port selection not working for your case? The other issue we've seen is machines tend to get overloaded with tons of agents running tests concurrently, hence the SSH remote isolation mode.

New comment by ammario in "A desktop app for isolated, parallel agentic development"

ammario — Mon, 24 Nov 2025 16:19:35 +0000

Author of Mux here:

I started building it out that way but found it very challenging to create parity between the models. E.g. they have different tools, system prompts, interruption semantics, cost tracking etc. The spirit of the product is decoupling the LLM from the UI, so we went with a custom loop / tools that can perform decently across all models.

New comment by ammario in "Show HN: Cmux – Coding Agent Multiplexer"

ammario — Thu, 16 Oct 2025 00:16:41 +0000

I wrote up some tips on that here: https://cmux.io/prompting-tips.html — most of it is generally applicable outside of `cmux`

Show HN: Cmux – Coding Agent Multiplexer

ammario — Wed, 15 Oct 2025 17:40:26 +0000

HN,

I'm stoked to share this product I've been working on non-stop for the past few weeks. It's an immersive GUI experience for working with many coding agents in parallel. The UX should be familiar to Claude Code users, but we took advantage of the GUI nature to add in a bunch more.

cmux is early but certainly usable—almost all of our internal cmux development rolls through cmux itself. Please let me know your thoughts and feedback!

Comments URL: https://news.ycombinator.com/item?id=45596024

Points: 22

# Comments: 4

New comment by ammario in "Fine-grained HTTP filtering for Claude Code"

ammario — Mon, 22 Sep 2025 21:49:48 +0000

I meant read-only there in the sense of mutability, not exfiltration.

Of course, some websites may permit mutations through GET so it’s probably only sensible to use alongside known hosts.

Fine-grained HTTP filtering for Claude Code

ammario — Mon, 22 Sep 2025 19:49:02 +0000

Article URL: https://ammar.io/blog/httpjail

Comments URL: https://news.ycombinator.com/item?id=45338561

Points: 88

# Comments: 11

Show HN: Httpjail – HTTP(s) request filter for processes

ammario — Mon, 15 Sep 2025 20:18:05 +0000

I originally built this as a way to make it safer to give CLI coding agents more autonomy. I wrote about that particular use case here: https://ammar.io/blog/httpjail.

Any feedback is appreciated!

Comments URL: https://news.ycombinator.com/item?id=45254423

Points: 4

# Comments: 0

New comment by ammario in "Anyclaude – Claude Code with Any LLM"

ammario — Sun, 10 Aug 2025 16:03:46 +0000

/shrug

The implementation is so simple it's quite the cat and mouse game if they want to become litigious

Anyclaude – Claude Code with Any LLM

ammario — Sat, 09 Aug 2025 20:29:42 +0000

Article URL: https://github.com/coder/anyclaude

Comments URL: https://news.ycombinator.com/item?id=44849905

Points: 2

# Comments: 2

Kalshi Exchange Statistics

ammario — Sat, 22 Feb 2025 21:34:33 +0000

Article URL: https://greed.bot/

Comments URL: https://news.ycombinator.com/item?id=43143489

Points: 3

# Comments: 0

New comment by ammario in "Making Markets on Kalshi"

ammario — Wed, 19 Feb 2025 01:14:38 +0000

Unfortunately collaboration here would kill my alpha ;)

New comment by ammario in "Making Markets on Kalshi"

ammario — Tue, 18 Feb 2025 03:34:54 +0000

I've been recording every trade across the platform for the past 3 months, which is when I began my operation.

Median Daily Volume (M$)

Dec 2024 - 10.2

Jan 2025 - 5.04

Feb 2025 - 5.89

So, in short, my data is inconclusive. I've been impressed with their marketing and business development though. They seem to be cozy with the new administration and I imagine any headwinds they had from the CFTC are disappearing.

New comment by ammario in "Making Markets on Kalshi"

ammario — Mon, 17 Feb 2025 21:02:23 +0000

Cool to see. I'm currently #1 on the Kalshi volume leaderboard (https://kalshi.com/social/leaderboard) with a proprietary market making algorithm.

There is plenty of money to be made on Kalshi, but I had to rethink the math from the ground up as most of the literature describes highly liquid, somewhat stable markets.

One small change you could make to your algorithm is to calculate the skews/spreads in log-odds space. A change in price from 50c to 49c represents a very small delta in expected return whereas 2c to 1c is a doubling. Dealing with probability contracts in log-odds controls for this effect.

New comment by ammario in "Making Markets on Kalshi"

ammario — Mon, 17 Feb 2025 20:54:54 +0000

Daily trading volume is about ~$5m

New comment by ammario in "Don't defer Close() on writable files (2017)"

ammario — Wed, 11 Sep 2024 04:55:17 +0000

I think this post overhypes the issue. So many writes we do just aren’t that important (e.g. logs, cli config, blah), Close fails rarely, and it’s pretty standard for casually developed application software to misbehave once the disk is full or breaking.

This is a classic safety / performance trade off that was properly selected in favor of performance.

The defer Close() is still quite useful as a way to avoid fd leaks.

Show HN: labeler – automatically label GitHub issues

ammario — Fri, 06 Sep 2024 17:34:01 +0000

We've been using this on mature OSS projects as well as internal repos @coder with good success. I figured it would be useful to the broader community. It's the kind of thing that saves a few minutes a day. So, not groundbreaking, but makes GitHub work slightly more pleasant.

Comments URL: https://news.ycombinator.com/item?id=41468105

Points: 1

# Comments: 0

New comment by ammario in "Web scraping with GPT-4o: powerful but expensive"

ammario — Mon, 02 Sep 2024 22:22:40 +0000

To scale such an approach you could have the LLM generate JS to walk the DOM and extract content, caching the JS for each page.