Hacker News: sh3rl0ck

New comment by sh3rl0ck in "Incident with Issues and Webhooks – Resolved"

sh3rl0ck — Mon, 04 May 2026 16:49:30 +0000

I've been a strong proponent of reallocating all LinkedIn server capacity to GitHub.

New comment by sh3rl0ck in "Everything that went wrong with Claude"

sh3rl0ck — Mon, 27 Apr 2026 07:45:29 +0000

Everything that went wrong with Claude so far.

New comment by sh3rl0ck in "CERN uses tiny AI models burned into silicon for real-time LHC data filtering"

sh3rl0ck — Sat, 28 Mar 2026 08:28:10 +0000

There's no mention of SLMs or LLMs, though.

> This work represents a compelling real-world demonstration of “tiny AI” — highly specialised, minimal-footprint neural networks

FPGAs for Neural Networks have been s thing since before the LLM era.

New comment by sh3rl0ck in "Google Workspace CLI"

sh3rl0ck — Thu, 05 Mar 2026 02:08:45 +0000

One of the very few good things from the AI race has been everyone finally publishing more data APIs out in the open, and making their tools usable via CLIs (or extensible APIs).

New comment by sh3rl0ck in "New iPad Air, powered by M4"

sh3rl0ck — Mon, 02 Mar 2026 15:02:00 +0000

I assume it's an economies of scale thing now.

It's not like Apple is putting any thought into either the UX or the engineering side of utilising the compute properly (except calculating those glass effects extra inefficiently).

Minimise SKUs and get some use out of the binned chips who have a few failed cores.

New comment by sh3rl0ck in "AI Made Writing Code Easier. It Made Being an Engineer Harder"

sh3rl0ck — Sun, 01 Mar 2026 15:46:50 +0000

I think there's a reward for finesse too.

As you mentioned, scope definition and constraints play a major role but ensuring that you don't just go for the first slop result but refine it pays off. It helps to have a very clear mental model of feature constraints that doesn't fall prey to scope creep.

New comment by sh3rl0ck in "Dear Time Lords: Freeze Computers in 1993"

sh3rl0ck — Fri, 27 Feb 2026 06:08:00 +0000

In Gallifrey? In Gallifrey.

New comment by sh3rl0ck in "Microsoft account bugs locked me out of Notepad – Are thin clients ruining PCs?"

sh3rl0ck — Sun, 08 Feb 2026 13:17:37 +0000

Never had Nvidia issues on Fedora and Ubuntu so far, 1P a multi computer research lab as well.

New comment by sh3rl0ck in "CCC (Claude's C Compiler) on Compiler Explorer"

sh3rl0ck — Sun, 08 Feb 2026 13:13:01 +0000

I find this a tad funny since ccc is my claude code alias, since cc is taken up by the actual, working, greatly optimised and really well made Clang C compiler.

New comment by sh3rl0ck in "uLauncher"

sh3rl0ck — Sun, 08 Feb 2026 13:07:42 +0000

It doesn't "require" a launcher at all; but the people have the freedom to change theirs.

Kinda like MacOS users only have Aqua, whereas Linux has a lot of DEs, the choice of which is entirely handed to the user.

New comment by sh3rl0ck in "Slop Terrifies Me"

sh3rl0ck — Sun, 08 Feb 2026 13:04:39 +0000

The poor maids and servants, the poor chauffeur, the poor chef, etc.

New comment by sh3rl0ck in "Why I Joined OpenAI"

sh3rl0ck — Sat, 07 Feb 2026 14:06:00 +0000

'Before you joined' seems to that she doesn't anymore.

I find it a little amusing that AI companies provide free AI subscriptions to their employees and their families. Perhaps because I'd never thought of it that way.

That's kinda nice actually; I assume employees get early access to models to test (5.3 codex, for example). Do families get it too?

New comment by sh3rl0ck in "I've reported on UFO sightings for decades – and come to this conclusion"

sh3rl0ck — Thu, 29 Jan 2026 17:22:16 +0000

Should be, but sadly isn't; the incentive is to feed into the economically incentivised "bs" rather than be wary of it, which is just... disheartening. Schools often inculcate this enough on a subconscious level that I've seen my fellow college mates rather unable to shake off that residual behaviour.

New comment by sh3rl0ck in "AI on Australian travel company website sent tourists to nonexistent hot springs"

sh3rl0ck — Thu, 29 Jan 2026 17:16:48 +0000

My problem with AI support agents is that instead of being good classifiers for my problem, they're even more non deterministic now in terms of grievance or query redressal. If a listed option is not available, I'd rather talk to a human who'd know or have the ability to find out, instead of an LLM which would just make something up with no grounding.

New comment by sh3rl0ck in "Does Anthropic believe its AI is conscious, or just want Claude to think so?"

sh3rl0ck — Thu, 29 Jan 2026 17:14:19 +0000

Yeah, I feel Anthropic is just very deliberately theatrical about the way they present their technology and company and even how they price them. Dario's conviction seems too over dramatic to be real to me, but while there's a chance he's drinking his own kool-aid, they just know how to present it as a premium experience, and their developer adoption helps with that.

New comment by sh3rl0ck in "Claude Code daily benchmarks for degradation tracking"

sh3rl0ck — Thu, 29 Jan 2026 17:10:31 +0000

I'd wager that lower tok/s vs lower quality of output would be two very different knobs to turn.

New comment by sh3rl0ck in "Moltworker: a self-hosted personal AI agent, minus the minis"

sh3rl0ck — Thu, 29 Jan 2026 17:07:44 +0000

On one hand, with the top comments of the rebrand post showing how many insecure deployments there are, something like this alongside cloudflare zero trust is probably a much more secure solution.

On the other hand, I just wanna point out

> Firstly, Cloudflare Workers has never been so compatible with Node.js. Where in the past we had to mock APIs to get some packages running, now those APIs are supported natively by the Workers Runtime.

Deployed a project a couple of days ago, and compared to past attempts where I had to wrangle (pun intended) with certain configs for deployment styles for node based applications, the normal build tooling just worked out of the box. Planning to move a couple of my free-from-me high DAU user projects that are on the vercel premium tier over to CF workers.

New comment by sh3rl0ck in "The Sovereign Tech Fund invests in Scala"

sh3rl0ck — Thu, 29 Jan 2026 16:57:32 +0000

What would you categorise as a "cool looking job"?

New comment by sh3rl0ck in "Winapp, the Windows App Development CLI"

sh3rl0ck — Thu, 29 Jan 2026 15:06:32 +0000

I'm 20 and I read Winamp, ha.

I reckon that the majority of the HN audience is into older (perhaps more graceful) working technology despite all the fanfare that newer, shinier stuff garners.

New comment by sh3rl0ck in "Provide agents with automated feedback"

sh3rl0ck — Mon, 19 Jan 2026 03:26:30 +0000

Beyond Linting and Shell Exec (gh, Playwright etc), what other additional tools did you find useful for your tasks, HN?!

Most of my feedback that can be automated is done either by this or by fuzzing. Would love to hear about other optimisations y'all have found.