Hacker News: ssk42

New comment by ssk42 in "Tell HN: OpenAI silently removed Study Mode from ChatGPT"

ssk42 — Sun, 12 Apr 2026 15:49:08 +0000

If I recall correctly, in their pivot to Codex they took a sizable amount of compute away from ChatGPT

New comment by ssk42 in "Grief and the AI split"

ssk42 — Fri, 13 Mar 2026 14:48:59 +0000

I’m sorry but in this day and age, why would you not use AI with safeguards? With giving it the proper context and best practices you’re looking for. These are all very solved in Claude and any agentic system. Are you saying that you don’t? This just feels insulting to those of us who do care about code but do love Claude

New comment by ssk42 in "Debian decides not to decide on AI-generated contributions"

ssk42 — Wed, 11 Mar 2026 14:07:57 +0000

Can you defend that though? Does living mean needing cells? Does it mean possessing the ability to think and reason? Is Claude thinking and reasoning?

New comment by ssk42 in "Agents that run while I sleep"

ssk42 — Wed, 11 Mar 2026 13:34:51 +0000

What

New comment by ssk42 in "Agents that run while I sleep"

ssk42 — Wed, 11 Mar 2026 03:12:12 +0000

Well I mean yes. I think people ought be aware for how the harnesses compare for their stacks. But clean room applies for this RGR situation too

New comment by ssk42 in "Agents that run while I sleep"

ssk42 — Tue, 10 Mar 2026 23:12:51 +0000

Fun to see you not on tildes.

Setting up a clean room is one of the only ways to do Evals on agentic harnesses. Especially prevalent with Windsurf which doesn’t have an easy CLI start.

So how? The easiest answer when allowed is docker. Literally new image per prompt. There’s also flags with Claude to not use memory and from there you can use -p to have it just be like a normal cli tool. Windsurf requires manual effort of starting it up in a new dir.

New comment by ssk42 in "OpenAI, the US government and Persona built an identity surveillance machine"

ssk42 — Tue, 24 Feb 2026 19:10:01 +0000

ClawdBots can now more easily interact with the Internet than regular agents, so you wind up with Moltbook leaking

New comment by ssk42 in "Kimi Claw"

ssk42 — Sun, 15 Feb 2026 21:58:28 +0000

Probably. It was on my tiktok FYP

New comment by ssk42 in "Kimi Claw"

ssk42 — Sun, 15 Feb 2026 15:34:32 +0000

The biggest clue I’ve seen is someone using it to do cold calls on websites. Claw searches for shoddy-looking construction sites, makes a better version on Vercel, and sends out a pitch.

New comment by ssk42 in "I vibe coded an iPhone app that I now use every day"

ssk42 — Tue, 13 Jan 2026 14:27:28 +0000

I saw an interesting comment somewhere that this will ultimately be Anthropic’s goal: creating the next generation of of App Store. The idea that Anthropic could just be building the mini vibe code to whatever the user wants. This post clearly exemplifies that me-apps can and should be a thing. That anyone can put forth reasonable effort and make an app without having to cross hard learning barriers of effort.

New comment by ssk42 in "Claude Code on the web"

ssk42 — Tue, 21 Oct 2025 16:44:29 +0000

People do build in public from vibe-coding, absolutely. This tells me that you have not done your research and just gone off of general guesses or pessimism/frustration from not knowing how to use the tool. The easiest way to be able to find this on Github is to look for where Claude is a contributor. Claude will tag itself in the PR or pushes. Another easy way to that I've seen come up for this is there is a whole "BuildInPublic" tag in the Threads app which has been inundated with Vibe coding. While these might not be in your algorithm, they do exist. You'll be able to see that while there is a lot of crud that there are also products being made are actually versatile, complex, and completely vibe-coded. Most people are not making up these stories. It's very real.

New comment by ssk42 in "Claude Code on the web"

ssk42 — Tue, 21 Oct 2025 14:21:46 +0000

Context engineering is a critical part of being able to use the tool. And it's ok to not understand how to use a new tool. The different models combined with different stacks require different ways of grappling with the technology. And it all changes! It sucks that you've tried it for your stack (Elixir, whatever that is) in your way and it was disappointing.

To me, the tool inherently makes sense and vibes with my own personality. It allows me to write code that I would otherwise procrastinate on. It allows me to turn ideas into reality, so much faster.

Maybe you're just hyper focused on metrics? Productivity, especially when dealing with code, is hard to quanitfy. This is a new paradigm and so it's also hard to compare apples to oranges. Does this help?

New comment by ssk42 in "Claude Sonnet will ship in Xcode"

ssk42 — Fri, 29 Aug 2025 02:33:26 +0000

Gosh, it's almost like a proper IDE has synonymous features with LLMs

New comment by ssk42 in "Emailing a one-time code is worse than passwords"

ssk42 — Thu, 07 Aug 2025 14:50:37 +0000

the good news is that you can self-host bitwarden pretty easily and so it doesn't have to be a hassle/risk

New comment by ssk42 in "Google suffers data breach in ongoing Salesforce data theft attacks"

ssk42 — Wed, 06 Aug 2025 18:50:32 +0000

Yeah, they have the world class Salesforce engineers there. One of Google's Salesforce's last tech leads wound up becoming the Director of the proprietary Salesforce language Apex.

New comment by ssk42 in "Claude Opus 4.1"

ssk42 — Tue, 05 Aug 2025 19:35:51 +0000

You can also always have it create design docs and mermaid diagrams for each task. Outline the why much easier earlier, shifting left

New comment by ssk42 in "Claude Code weekly rate limits"

ssk42 — Mon, 28 Jul 2025 20:16:50 +0000

Used to be? What changed?

New comment by ssk42 in "Everything around LLMs is still magical and wishful thinking"

ssk42 — Fri, 04 Jul 2025 22:52:27 +0000

What exactly are you basing any of your assertions off of?

New comment by ssk42 in "Apple patents suggest future AirPods could monitor biosignals and brain activity"

ssk42 — Tue, 10 Oct 2023 23:19:26 +0000

Search for "daylist" on Spotify and it'll come up with exactly that

New comment by ssk42 in "What's wrong with in-browser cryptography?"

ssk42 — Tue, 31 Dec 2013 07:20:03 +0000

So this will also probably be another seemingly clueless question, but after reading up on air gapped computers, how would that help with the new hash?