Hacker News: Veen

New comment by Veen in "Nvidia NemoClaw"

Veen — Wed, 18 Mar 2026 20:07:43 +0000

What does any of this have to do with Israel?

New comment by Veen in "Obsidian Sync now has a headless client"

Veen — Sat, 28 Feb 2026 19:25:38 +0000

It would be nice if one could sync dot files in the vault. For example, the .claude or .pi folder containing skills and whatnot.

New comment by Veen in "The United States and Israel have launched a major attack on Iran"

Veen — Sat, 28 Feb 2026 11:06:45 +0000

Iran attacks through its proxies.

New comment by Veen in "Setting up OpenClaw on a cloud VM"

Veen — Fri, 27 Feb 2026 20:16:21 +0000

It's not a soluble problem, at least not completely. The big frontier models are better at resisting prompt injection, but any LLM is vulnerable to some degree. If you give it access to arbitrary inputs like the web and to your personal data, there's a risk it'll disclose stuff you don't want it to.

It's annoying, because I love OpenClaw as an idea, but I don't trust it enough to give it what it needs to be useful.

New comment by Veen in "Pi – A minimal terminal coding harness"

Veen — Wed, 25 Feb 2026 21:33:53 +0000

Its original name was more distinctive but less "enterprise friendly".

https://shittycodingagent.ai

New comment by Veen in "Claws are now a new layer on top of LLM agents"

Veen — Sat, 21 Feb 2026 21:11:19 +0000

Also more vulnerable to prompt injection than the frontier models, which are still vulnerable, but less so.

New comment by Veen in "Claws are now a new layer on top of LLM agents"

Veen — Sat, 21 Feb 2026 21:09:21 +0000

> CME's website is very bot-hostile and blocked it after a few requests

This is one of the reasons people buy a Mac mini (or similar local machine). Those browser automation requests come from a residential IP and are less likely to be blocked.

New comment by Veen in "Anthropic officially bans using subscription auth for third party use"

Veen — Thu, 19 Feb 2026 09:03:50 +0000

Many people use the Max subscription OAuth token in OpenClaw. The main chat, heartbeat, etc., functionality does not call the Claude Code CLI. It uses the API authenticated via subscription OAuth tokens, which is precisely what Anthropic has banned.

There are many other options too: direct API, other model providers, etc. But Opus is particularly good for "agent with a personality" applications, so it's what thousands of OpenClaw users go with, mostly via the OAuth token, because it's much cheaper than the API.

New comment by Veen in "OpenClaw is basically a cascade of LLMs in prime position to mess stuff up"

Veen — Tue, 03 Feb 2026 22:22:21 +0000

There's a lot of, to put it lightly, bullshit in this blog article, starting with when openclaw was released (late November 2025, not January 25, 2026). The first bit of config — "listen: "0.0.0.0:8080" — is not the default. Default is loopback and it was when I first encounter this project at the end of December.

Essentially, the author has deliberately misconfigured an openclaw installation so it is as insecure as possible, changing the defaults and ignoring the docs to do so. Lied about what they've done and what the defaults are. Then "hacked" it using the vulnerability they created.

That said, there are definite risks to using something like openclaw and people who don't understand those risks are going to get compromised, but that doesn't justify blatant lying.

New comment by Veen in "OpenClaw – Moltbot Renamed Again"

Veen — Fri, 30 Jan 2026 08:15:44 +0000

More that moltbot is ugly and was chosen in a bit of a panic after Anthropic complained. No one liked it, including the people who chose it.

New comment by Veen in "Clawdbot Renames to Moltbot"

Veen — Tue, 27 Jan 2026 23:12:45 +0000

They've recently added "lobster" which is an extension for deterministic workflows outside of the LLM, at least partially solving that problem. Also fixed a context caching bug that resulted in it using far more Anthropic tokens than it should have.

New comment by Veen in "Clawdbot Renames to Moltbot"

Veen — Tue, 27 Jan 2026 21:36:56 +0000

It's not. The guy behind Moltbot dislikes crypto bros as much as you seem to. He's repeatedly publicly refused to take fees for the coin some unconnected scumbags made to ride the hype wave, and now they're attacking him for that and because he had to change the name. The Discord and Peter's X are swamped by crypto scumbags insulting him and begging him to give his blessing to the coin. Perhaps you should do a bit of research before mouthing off.

New comment by Veen in "Is It Time for a Nordic Nuke?"

Veen — Mon, 26 Jan 2026 17:27:22 +0000

How do envision we might disarm an adversary with thousands of nuclear missiles, other than by preemptively nuking them and hoping they don't respond in time. Not really a plausible plan.

New comment by Veen in "A Brief History of Ralph"

Veen — Mon, 19 Jan 2026 19:16:12 +0000

You probably wouldn't use it for anything serious, but I've Ralphed a couple of personal tools: Mac menu bar apps mostly. It works reasonably well so long as you do the prep upfront and prepare a decent spec and plan. No idea of the code quality because I wouldn't know good swift code from a hole in the head, but the apps work and scratch the itch that motivated them.

New comment by Veen in "I know you didn't write this"

Veen — Mon, 22 Dec 2025 19:47:35 +0000

Yes, I write everything in Obsidian and use "Paste from Markdown" in Google Docs. It's a habit I picked up years ago when Docs was much less reliable and lost work.

Plus, I want to deliver the completed document, not my edit history. Even on the occasions that I have written directly in Google Docs, I've copied the doc to obliterate the version history.

New comment by Veen in "Structured outputs create false confidence"

Veen — Sun, 21 Dec 2025 17:07:52 +0000

Doesn't the Claude APIs recently introduced ability to combine extended thinking with structured outputs overcome this issue? You get the unconstrained(ish) generation in the extended thinking blocks and then structured formatting informed by that thinking in the final output.

New comment by Veen in "Oliver Sacks put himself into his case studies – what was the cost?"

Veen — Fri, 19 Dec 2025 08:31:15 +0000

I'd always assumed that the patients in Sacks' books were lightly fictionalized composites that combined interesting features from multiple cases. The purpose being to illustrate conditions and aspects of human psychology for a general readership. Since they weren't presented as rigorous case studies, I didn't take them to be that. I find what Sacks did much less irksome than more recent psychological and social studies books that pretend to be presenting rigorous scientific fact when they are, in fact, tendentious bullshit.

New comment by Veen in "OpenAI are quietly adopting skills, now available in ChatGPT and Codex CLI"

Veen — Sat, 13 Dec 2025 08:24:45 +0000

Small use case but I’m using skills for analysing and scoring content then producing charts. LLM does the scoring then calls a Python script bundled in the skill that makes a variety of PNG charts based on metrics passed in via command line arguments. Claude presents the generated files for download. The skill.md file explains how to run the analysis and how to call the script and with what options. That way, you can get very consistent charts because they’re generated programmatically, but you can use the LLM for what it’s good at.

New comment by Veen in "The fuck off contact page"

Veen — Mon, 08 Dec 2025 10:01:31 +0000

A lot of it is internal politics. As a consultant, you see the tip of the iceberg. There may be rational reasons for seemingly irrational decisions that you're not privy to. Your contact's boss wants it done some particular way, so your contact insists on doing it that way. Or your contact has recommended doing it some way internally, and they don't want to be made to look a fool by an outside consultant. Etc.

New comment by Veen in "The fuck off contact page"

Veen — Mon, 08 Dec 2025 09:52:58 +0000

You have to judge it client by client though. Some are amenable to and grateful for a flatly stated analysis and recommendation, even if it goes against their ideas. Some will feel belittled and undermined. You need both sorts to pay their invoices and refer their peers, so you pick your battles.