Hacker News: EGreg

New comment by EGreg in "What is it like to be a bat? (1974) [pdf]"

EGreg — Thu, 11 Jun 2026 04:18:52 +0000

Oh, I’d say they had some good clues.

New comment by EGreg in "AI agent runs amok in Fedora and elsewhere"

EGreg — Thu, 11 Jun 2026 04:16:33 +0000

Literally on the front page of https://safebots.ai … “Don’t let your AI Agents run amok”. Sadly we will see a proliferation of not just agents, but swarms

New comment by EGreg in "Building an HTML-first site doubled our users overnight"

EGreg — Wed, 10 Jun 2026 15:57:47 +0000

I think Facebook with their money and Vercel with their VC funding tried hard to push the React and then the Next.js everywhere. So it arrived in time for AIs to all train on it. And now it’s the one true way :)

But do we really need all that stuff? Build steps, bundling, tree shaking, all for what? And is it really simpler… hmm

New comment by EGreg in "Hermes Agent – Open-source AI agent with persistent memory"

EGreg — Tue, 09 Jun 2026 02:54:08 +0000

What's wrong with having a website where you scan a QR code, and have your own private chat, and it sends notifications using, say, Web Push?

New comment by EGreg in "The 29th International Obfuscated C Code Contest (IOCCC) 2025 Winners"

EGreg — Sun, 07 Jun 2026 20:17:59 +0000

Wait, I kind of don't get it.

So Obfuscated C Code Contest works but Capture the Flag doesn't? Because of AI?

https://twit.tv/posts/tech/ai-disrupts-capture-flag-what-mea...

New comment by EGreg in "LLMs are eroding my software engineering career and I don't know what to do"

EGreg — Sun, 07 Jun 2026 14:58:02 +0000

Think of it like this

You’ve already faced this the entire time with… libraries on github.

If employers knew how much you can just use a new standard library, or ask you to “use React”, that’s a lot like asking you to use an LLM to speed things up. You also benefit from the collective wisdom of a lot of people. Do you write assembly or pixel shaders by hand?

Autohost – spin up websites seconds after someone points a domain at them

EGreg — Fri, 05 Jun 2026 22:32:48 +0000

Article URL: https://github.com/Safebots/Autohost

Comments URL: https://news.ycombinator.com/item?id=48419200

Points: 2

# Comments: 0

Worried about Recursive Self-Improvement (RSI)? The answer might be CDE

EGreg — Fri, 05 Jun 2026 07:42:06 +0000

Article URL: https://safebots.ai/declarative.html

Comments URL: https://news.ycombinator.com/item?id=48409319

Points: 1

# Comments: 0

New comment by EGreg in "When AI Builds Itself: Our progress toward recursive self-improvement"

EGreg — Fri, 05 Jun 2026 07:21:33 +0000

RSI is dangerous. That is why we designed CDE:

https://safebots.ai/declarative.html

New comment by EGreg in "How we index images for RAG"

EGreg — Tue, 02 Jun 2026 22:01:55 +0000

We have it in our open-source framework, in case anyone wants to deploy it:

https://github.com/Qbix/AI/blob/6753f6e453908682401f49760002...

https://github.com/Qbix/AI/blob/main/config/observations.jso...

wrote it up here a few months ago: https://community.safebots.ai/t/building-cultural-infrastruc...

What AI slop (on LinkedIn and elsewhere) now reads like

EGreg — Tue, 02 Jun 2026 18:18:29 +0000

Article URL: https://magarshak.com/blog/the-one-insight-that-separates-high-performers-from-everyone-else-its-not-what-you-think/

Comments URL: https://news.ycombinator.com/item?id=48374061

Points: 1

# Comments: 1

New comment by EGreg in "Malicious npm packages detected across Red Hat Cloud Services"

EGreg — Mon, 01 Jun 2026 19:32:27 +0000

https://qbix.com/blog/2026/04/01/no-way-to-prevent-this-says...

New comment by EGreg in "SQLite is all you need for durable workflows"

EGreg — Fri, 29 May 2026 18:03:06 +0000

Files is all you need.

https://xkcd.com/378/

New comment by EGreg in "I think Anthropic and OpenAI have found product-market fit"

EGreg — Thu, 28 May 2026 21:34:36 +0000

And how exactly does the agent harness surface ALL the right places that need to be updated, and reason about functions and APIs?

New comment by EGreg in "I think Anthropic and OpenAI have found product-market fit"

EGreg — Wed, 27 May 2026 17:33:06 +0000

Here is a serious question.. Can we sell into the hype cycle and on the way down with this: https://safebots.ai/costs.html

New comment by EGreg in "I think Anthropic and OpenAI have found product-market fit"

EGreg — Wed, 27 May 2026 17:32:10 +0000

Most work is not coding.

And also, people have it wrong… their models are not the main problem anymore. It’s the RAG

New comment by EGreg in "Why AI Agents Cannot Change Software Systems"

EGreg — Wed, 27 May 2026 14:38:13 +0000

"But agentic work is global and transformative: the LLM must change the system itself, which requires understanding dependencies, invariants, interactions, and downstream consequences.

This is causal reasoning, not pattern extension. LLMs predict tokens, not consequences — and that is why the leap from writing code to producing a safe, system‑aware PR‑ready diff is not incremental but a shift into a fundamentally different problem space."

This is well said. We need a new paradigm. I could go into the shortcomings of the current agent-oriented approaches but it would turn into a huge post. If you want to read it, I wrote it up here: http://safebots.ai/agents.html

New comment by EGreg in "Claude Code as a Daily Driver: Claude.md, Skills, Subagents, Plugins, and MCPs"

EGreg — Wed, 27 May 2026 13:10:10 +0000

Best Claude Code daily-driver guide I’ve read. Though I’ve only read two. The “let Claude write rules for itself” CLAUDE.md pattern is the highest-ROI habit in there. Buth here’s the thing. The assumption underneath: this works when Claude mostly follows CLAUDE.md. Anthropic’s own engineering post from May 25 (https://www.anthropic.com/engineering/how-we-contain-claude) reports their telemetry shows ~93% of permission prompts get clicked through and ~17% of dangerous actions slip past the auto-mode filter.

Their conclusion: environment-layer containment first, then model-layer steering. CLAUDE.md is the right configuration layer but it is not a containment layer. Worth thinking about whether your worst case is a lost afternoon or a lost database and all backups deleted, too: https://safebots.ai/compromise.html

But the more important point are the costs. People are starting to realize just how costly it can be to run agents without precomputing and caching: https://safebots.ai/costs.html and self-orchestrating agents can go up to 1000x: https://safebots.ai/kimi.html

New comment by EGreg in "What color is your function? (2015)"

EGreg — Wed, 27 May 2026 01:30:45 +0000

Actually, it's not async programming. It's only async programming the way JS does it... which is unwinding the entire stack, and then starting another stack on the next tick.

Instead, many languages have fibers / coroutines / etc. which simply start new stacks elsewhere, and capture the context.

New comment by EGreg in "Cloudflare Flagship"

EGreg — Wed, 27 May 2026 00:32:51 +0000

If anyone is interested, you can implement something like that with a few lines of code on the front end. We expose a function that generates a uniformly-distributed hash that you can use for A/B testing and other uses:

  Q.Data.variant()

https://github.com/Qbix/Q.js/blob/main/src/js/Q.minimal.js#L...

And on the back end, you'd use it like this:

https://github.com/Qbix/Platform/blob/main/platform/classes/...

Essentially, this can support a huge number of "variants" and within each variant you can have N equal segments. That will help you do A/B testing and flipping features on or off.