Viewing profile — Veen
Veen
HN member- Joined
- Tue, Aug 16, 2016, 1:08 PM UTC
- HN karma
- 9,773
- Public activity
- 2,838 items
- HN profile
- View on Hacker News ↗
About Veen
No profile information was provided.
Recent public activity
-
comment
Comment #47430772
What does any of this have to do with Israel?
- comment
-
comment
Comment #47199182
It would be nice if one could sync dot files in the vault. For example, the .claude or .pi folder containing skills and whatnot.
-
comment
Comment #47193677
Iran attacks through its proxies.
-
comment
Comment #47184982
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 acce…
-
comment
Comment #47158206
Its original name was more distinctive but less "enterprise friendly". https://shittycodingagent.ai
-
comment
Comment #47104812
Also more vulnerable to prompt injection than the frontier models, which are still vulnerable, but less so.
-
comment
Comment #47104783
> 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 reques…
-
comment
Comment #47071621
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 sub…
-
comment
Comment #46878184
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 — "…
- comment
-
comment
Comment #46821812
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.
-
comment
Comment #46788529
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 tha…
-
comment
Comment #46787260
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 …
-
comment
Comment #46768585
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 plausibl…
-
comment
Comment #46683174
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 upfron…
- comment
-
comment
Comment #46358101
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…
- comment
-
comment
Comment #46346277
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 exten…
-
comment
Comment #46323551
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 c…
-
comment
Comment #46253042
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 varie…
-
comment
Comment #46190490
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 c…
-
comment
Comment #46190410
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…
-
comment
Comment #45914789
That and people who want to use it to make porn.