Hacker News: chatmasta

New comment by chatmasta in "If you don't run your own LLM proxy, how do you know whats going on?"

chatmasta — Mon, 19 Oct 2026 12:31:11 +0000

Any org with more than 150 employees needs to pay API prices for the enterprise subscription.

New comment by chatmasta in "Strengthening our defenses against distillation attacks"

chatmasta — Tue, 13 Oct 2026 03:27:59 +0000

It also reads like an advertisement for a watering hole full of sensitive credentials and operational details from adversaries of the US government.

New comment by chatmasta in "Strengthening our defenses against distillation attacks"

chatmasta — Tue, 13 Oct 2026 03:26:30 +0000

Huh? Are Claude prompts attached to GitHub commits?

New comment by chatmasta in "OpenAI fires three safety researchers for "mishandling research information""

chatmasta — Fri, 09 Oct 2026 10:49:59 +0000

This is pretty common practice for EAs.

New comment by chatmasta in "Returning from vacation? The government can search your phone without a warrant"

chatmasta — Thu, 01 Oct 2026 14:20:56 +0000

They’d probably say it wasn’t selective enforcement, because the phone scan is a faster way to complete their investigation compared to an interrogation. It’s the same disclaimer used for a manual search when you opt out of the body scanner.

New comment by chatmasta in "Returning from vacation? The government can search your phone without a warrant"

chatmasta — Thu, 01 Oct 2026 14:18:33 +0000

My work computer seems to already have this feature!

New comment by chatmasta in "Cf: The Agentic CLI for the Cloudflare API"

chatmasta — Tue, 29 Sep 2026 02:22:11 +0000

You can write a CLI in typescript and bundle it into a a single JS file. In fact (without looking) I’m sure that’s what Cloudflare is doing here because it’s standard practice.

New comment by chatmasta in "Launch HN: Vespper (YC F24) – SOTA Docx MCP"

chatmasta — Tue, 29 Sep 2026 02:21:17 +0000

The people who need this most are not going to want to use an external MCP server. This is a pretty unusual model for a narrowly scoped product offering like this. I was excited until I realized it’s not something I can run locally.

New comment by chatmasta in "Cf: The Agentic CLI for the Cloudflare API"

chatmasta — Mon, 28 Sep 2026 18:42:53 +0000

Typescript and the npm/JS ecosystem may be complex, but you don’t need AGI to figure out how to install a CLI built with TS. My agent can figure out how to install this.

New comment by chatmasta in "Don't let anyone take away your big box of cables"

chatmasta — Fri, 11 Sep 2026 13:17:34 +0000

I’ve long wanted to take a digital inventory of my big box (boxes) of cables, with photo, connector types, etc.

New comment by chatmasta in "Ask HN: Those making $500/month on side projects in 2026 – Show and tell"

chatmasta — Sun, 30 Aug 2026 03:22:58 +0000

There’s probably some selection bias here if people are close to death (either by suicide or terminal diagnosis) and looking for the solution.

New comment by chatmasta in "Ask HN: Those making $500/month on side projects in 2026 – Show and tell"

chatmasta — Sun, 30 Aug 2026 03:22:24 +0000

Just want to let you know that I appreciated this joke even if nobody else noticed it.

New comment by chatmasta in "Ask HN: How to break Claude Code addiction?"

chatmasta — Sun, 30 Aug 2026 03:17:24 +0000

Clear the session after 300k tokens and force your workflow to adapt to it. The rabbit holes come when you’re at context rot and blindly following Claude debugging some problem that you shouldn’t even be trying to solve.

Other than that, set an alarm when you want to stop working. When it rings, physically unplug your work laptop and move it somewhere out of sight.

New comment by chatmasta in "Ask HN: Which class of business model is most resilient to build in the AI era?"

chatmasta — Fri, 28 Aug 2026 00:40:49 +0000

Let me rephrase the question to the scope of startups. A small business is not a startup: https://www.paulgraham.com/growth.html

But you’re also completely right.

Ask HN: Which class of business model is most resilient to build in the AI era?

chatmasta — Thu, 27 Aug 2026 23:32:33 +0000

If you were to start a company today, what type of business model would you choose? Most new businesses have some form of AI in them, and this makes some sense during a gold rush, but it’s also a crapshoot. And the rate of change is so insanely fast and unpredictable that it’s becoming difficult to read the market with any confidence beyond three months. Even if you hit traction, there’s no guarantee your moat won’t evaporate. And it’s cheap for everyone to build now.

Personally I think the smartest business to start right now would be an “online-to-offline” model that bridges digital and physical world - think DoorDash, Uber, etc… if you hit traction with that kind of business then at least you have a legitimate moat that AI can’t drain overnight.

Comments URL: https://news.ycombinator.com/item?id=49472620

Points: 3

# Comments: 5

New comment by chatmasta in "Microduck"

chatmasta — Thu, 27 Aug 2026 23:22:50 +0000

Typing bash commands on a colleague’s French keyboard was one of the most frustrating experiences of my life.

New comment by chatmasta in "That time when I failed the Microsoft interview"

chatmasta — Tue, 04 Aug 2026 04:33:41 +0000

The candidate may have had more success if he saved the honesty for after he solved the riddle he claimed he already knew how to solve.

New comment by chatmasta in "Ten advances in mathematics and theoretical computer science"

chatmasta — Tue, 04 Aug 2026 04:18:40 +0000

I expect we can squeeze a lot more exponential out of LLMs because they’ve basically shown that human “consciousness,” insofar as it’s composed of knowledge and rules for synthesizing that knowledge, can be represented mathematically in a very high dimensional space. Why does this “just work?” Nobody really knows, but it clearly does.

However, I also expect this squeeze will come at an increasingly expensive price — not just because of inefficient token usage, but because of fundamental limitations of LLMs as a model.

LLMs are letting us brute force our way through a lot of reasoning, but it’s hard to believe that such a generic model of intelligence will take us to the next frontier. We’ll need some fundamentally new approaches at some point. Maybe those will make achieving the exponential more efficient or maybe they’ll unlock even higher degrees of possibility. Who knows?

New comment by chatmasta in "CosmosEscape: Taking over Every Database in Azure Cosmos DB"

chatmasta — Thu, 30 Jul 2026 16:15:29 +0000

There have been a lot. I remember one that was essentially “send the request without an Authorization header.”

New comment by chatmasta in "Our position on open-weights models"

chatmasta — Mon, 27 Jul 2026 22:38:54 +0000

Is China opposition unique to the current administration? Didn’t they soften the CHIPS act put in place by the previous one?