Hacker News: MrDarcy

New comment by MrDarcy in "A message from President Kornbluth about funding and the talent pipeline"

MrDarcy — Fri, 15 May 2026 02:46:33 +0000

This is insanity. Then let them learn by advancing their own goals, not the goals of their exploiter. I won’t even call it advising because it clearly is not as you yourself admit.

New comment by MrDarcy in "Claude for Legal"

MrDarcy — Fri, 15 May 2026 00:29:57 +0000

Your lawyer uses cloud software, this is no different.

New comment by MrDarcy in "Claude for Legal"

MrDarcy — Fri, 15 May 2026 00:22:26 +0000

IANAL but I believe discovery is where this would happen.

New comment by MrDarcy in "From Supabase to Clerk to Better Auth"

MrDarcy — Thu, 07 May 2026 01:45:06 +0000

Recently went with a vendor of an agentic observability and evaluation product built on Supabase and Clerk. The number of vulnerabilities and CVE’s and outright… I don’t even know the words, coming from this stack is staggering.

Be very very wary of any vendor selling something built on this Supabase + Clerk stack. That alone is a very strong indicator they do not understand basic security or data protection.

New comment by MrDarcy in "The agent harness belongs outside the sandbox"

MrDarcy — Sun, 03 May 2026 04:21:08 +0000

I can see that. It also seems like the first quickly evolves into the second.

New comment by MrDarcy in "The agent harness belongs outside the sandbox"

MrDarcy — Sun, 03 May 2026 04:11:00 +0000

The purpose of a sandbox is to control the interface between inside and outside of the sandbox. If you put the harness on the outside and connect it to a model and to an API then there’s no point in the sandbox. You don’t have any control over the interface.

New comment by MrDarcy in "The agent harness belongs outside the sandbox"

MrDarcy — Sat, 02 May 2026 23:41:17 +0000

> A lot of what an agent does doesn't need a sandbox at all: thinking, calling APIs, summarizing, waiting for CI.

I don’t get it. Calling an API requires a sandbox in most cases. The others could be abused in service of an un-sandboxed agent with API access.

If the harness is outside the sandbox then it’s just an ambiguous and confusing security model and boundary.

New comment by MrDarcy in "Uber Torches 2026 AI Budget on Claude Code in Four Months"

MrDarcy — Fri, 01 May 2026 18:28:09 +0000

It turns into 50k to 100k or more of value for the employee the moment upper management made AI spend a personal performance target across most corporations.

New comment by MrDarcy in "Google plans to invest up to $40B in Anthropic"

MrDarcy — Sat, 25 Apr 2026 00:56:41 +0000

The CTO/VP of engineering role down is now singularly focused on keeping agents fed with a backlog of Linear issues. This is the new normal.

New comment by MrDarcy in "Vercel April 2026 security incident"

MrDarcy — Sun, 19 Apr 2026 20:41:40 +0000

They’re all shit too. All three decided to do custom auth instead of OIDC and it’s a nightmare to integrate with any of them.

New comment by MrDarcy in "Vercel April 2026 security incident"

MrDarcy — Sun, 19 Apr 2026 20:39:52 +0000

Same for Go.

New comment by MrDarcy in "US summons bank bosses over cyber risks from Anthropic's latest AI model"

MrDarcy — Fri, 10 Apr 2026 18:13:30 +0000

I read your list and all of that is normal computer use. How can it be reckless to use a computer normally?

New comment by MrDarcy in "Why do we tell ourselves scary stories about AI?"

MrDarcy — Fri, 10 Apr 2026 15:10:19 +0000

This usage pattern is a few months behind the curve. It’s effective at full on feature development now. Keep it fed with plans and it’ll keep implementing, leaving the codebase better than it found it each cycle.

New comment by MrDarcy in "I quit. The clankers won"

MrDarcy — Wed, 01 Apr 2026 13:51:08 +0000

Not sure why this would catch heat rationally speaking. It is quite clear in a professional setting effective use of coding agents is the most important skill to develop as an individual developer.

It’s also the most important capability engineering orgs can be working on developing right now.

Software Engineering itself is being disrupted.

New comment by MrDarcy in "LinkedIn uses 2.4 GB RAM across two tabs"

MrDarcy — Sun, 29 Mar 2026 16:38:59 +0000

I have consulted for CEO’s and other executives who think like this. You certainly dodged a bullet.

New comment by MrDarcy in "Show HN: Optio – Orchestrate AI coding agents in K8s to go from ticket to PR"

MrDarcy — Wed, 25 Mar 2026 23:18:37 +0000

Looks cool, congrats on the launch. Is there any sandbox isolation from the k8s platform layer? Wondering if this is suitable for multiple tenants or customers.

New comment by MrDarcy in "First and Lego Education Partnership Update"

MrDarcy — Mon, 23 Mar 2026 03:06:18 +0000

I was a mentor for an all girls high school FIRST team and I have to say, the way they were treated at competition by other teams and the way the organization handled that sexual objectification of them at competition leads me to a “that checks out” conclusion of Kamen and Epstein.

Culture propagates from the top.

New comment by MrDarcy in "Is legal the same as legitimate: AI reimplementation and the erosion of copyleft"

MrDarcy — Tue, 10 Mar 2026 00:25:42 +0000

HN comments on LLM agents are bi-modal now, as are views in the general population. The modes are adopters and non-adopters.

There isn’t much of a middle ground anymore.

New comment by MrDarcy in "Training students to prove they're not robots is pushing them to use more AI"

MrDarcy — Sat, 07 Mar 2026 20:45:23 +0000

Is that not pointless now? The point of writing was previously to communicate our thoughts and ideas to other people. Now and going forward that is unnecessary. The most efficient and effective way for us to communicate our thoughts and ideas is to have an agent organize and write them down for us.

New comment by MrDarcy in "Tell HN: I'm 60 years old. Claude Code has re-ignited a passion"

MrDarcy — Sat, 07 Mar 2026 15:15:55 +0000

Why the downvotes? It is the defining characteristic of the staff+ level to empower others. Individual contributions don’t matter at this level.