Hacker News: abound

New comment by abound in "Signing TLS handshakes inside a TPM"

abound — Mon, 07 Sep 2026 03:45:39 +0000

Yeah I was interested for the first few paragraphs, then all of a sudden I get hit with two "genuinely"s and a

> That’s the third property, and it’s the one that decides this.

and I gave up at that point.

New comment by abound in "Changes to Sourcehut's terms of service regarding LLMs"

abound — Thu, 27 Aug 2026 13:42:44 +0000

I think this is more of a nitpick than anything. SourceHut is a code forge, code forges are where you store your code (and tickets). The policy going forward is a ban on using LLMs to write code (and tickets). The use cases listed there (reviewing work, asking questions, etc) are minority use cases and mostly would be unenforceable even if included in the policy.

New comment by abound in "Jabber/XMPP: 25 Years of Digital Independence"

abound — Mon, 24 Aug 2026 19:29:42 +0000

I recently migrated from Google Voice to jmp.chat, which is a telephony/SMS/etc bridge to XMPP. I use Dino on my laptop, and Cheogram on my phone, and the experience has been quite nice and seamless. Next step is to host my own Prosody server and import my whole Google Voice history.

New comment by abound in "Ordinary Abundance"

abound — Fri, 14 Aug 2026 01:25:09 +0000

To put a name on what a lot of folks in this thread are describing (I didn't see the term mentioned in the article): Negative Visualization [1].

Basically imagining living life without a given luxury (hot water, infinite music on tap, functioning eyesight, etc), really internalizing that feeling, and then practicing gratitude for the fact that you do indeed have that thing.

[1] https://en.wikipedia.org/wiki/Negative_visualization

New comment by abound in "How I use LLMs to learn complex topics"

abound — Sun, 09 Aug 2026 22:13:55 +0000

This is the exact opposite of what the parent comments are talking about.

New comment by abound in "Claude Code: Starting August 14, auto mode will be the default permission mode"

abound — Sat, 08 Aug 2026 00:37:34 +0000

I don't disagree with anything you said here, but I find auto-mode is too permissive on the reading side of things.

I used Claude this morning to convert the financial books for my nonprofit from some export of a proprietary software (Aplos) to plaintext accounting (Beancount), and was surprised to find it had found my personal Beancount ledger elsewhere on my hard drive and modelled its plan on that. That was correct and helpful, but a bit of an overreach in my opinion, enough that I'll be sandboxing agents (with tools like nono, smolmachines, etc) going forward.

New comment by abound in "My personal AI benchmark: “Generate an SVG of a frog with a Habsburg jaw”"

abound — Mon, 03 Aug 2026 01:32:32 +0000

My personal benchmark is a directory containing a bunch of research papers on the physics of popping popcorn kernels, and a prompt about creating high fidelity, photo realistic 3D models of all the different kinds of popped kernels. Fable (surprisingly? unsurprisingly?) refused to do it last time I tried, and the results from other models are, well, fine, but there's still plenty of headroom on this particular one.

New comment by abound in "Why Is Europe Burning?"

abound — Sun, 02 Aug 2026 02:59:19 +0000

Arson may be the original source, as may campfires, downed power lines, sparks from powered tools, etc, but the fact that these fires grow much larger than in the past is because of climate change.

If it wasn't humans, it'd be lightning strikes and other natural phenomena.

New comment by abound in "The session you cannot take with you"

abound — Fri, 31 Jul 2026 14:53:35 +0000

One reason to switch models mid-session that I didn't see explored in this post: cost. As we get ever-more-powerful models, it's going to make sense to use them for some exploratory/research/design phase, and then smaller models for other bits, within a single session. It'll likely even be managed automagically by another model that is just trained to do routing.

As people (and especially companies) adopt these tools for more and more usecases, there's just too much money being wasted on using an unnecessarily large model for a given job.

New comment by abound in "Delayed Gratification – Proud to Be 'Last to Breaking News'"

abound — Tue, 28 Jul 2026 19:41:16 +0000

Not yet, but I'll see if I can publish the basics for it this week.

New comment by abound in "Anthropeum – Where in the world, and when, does this human artifact belong?"

abound — Tue, 28 Jul 2026 17:51:49 +0000

In this context, "top 90%" means "bottom 10%". I did truly awful and got "top 99%", which sounded impressive until I realized what happened.

New comment by abound in "Delayed Gratification – Proud to Be 'Last to Breaking News'"

abound — Tue, 28 Jul 2026 17:26:29 +0000

Nope! Every source I care about either has an RSS feed, or I've been able to make a custom recipe [1] to handle things like auth for paid sites and whatnot.

[1] https://manual.calibre-ebook.com/glossary.html#term-recipe

New comment by abound in "Delayed Gratification – Proud to Be 'Last to Breaking News'"

abound — Tue, 28 Jul 2026 16:38:44 +0000

I've been building something similar for my own purposes. Basically, I use Calibre's "Fetch News" functionality to get epubs of all the news sources I trust, and then once a month (interval is configurable), I run a pipeline over all of it (some LLM magic, partly local partly API) to dedupe and rank stories, then compile it into an actual honest-to-goodness newspaper (using Typst for layout and stuff), then read that at my leisure.

New comment by abound in "Don't ask an LLM for a confidence score"

abound — Tue, 28 Jul 2026 14:39:04 +0000

> I asked it “do you think the model will generate a meaningful number there?”

This also isn't likely to give you good results, models don't have a good sense of their own capabilities.

This is also in the same camp of asking a model why it did something. It'll generate something plausible and likely totally incorrect.

New comment by abound in "If digital computers are conscious, they are conscious at the hardware level"

abound — Mon, 27 Jul 2026 20:55:42 +0000

A more charitable take is that we shouldn't tile the universe with consciousnesses that are in constant, unending agony. Torment Nexus and all that.

New comment by abound in "LLM Networking with MikroTik"

abound — Thu, 16 Jul 2026 01:58:58 +0000

> I have the agent write a script that is aimed to be idempotent and then run the script.

You can take this one step further and have the agent write Terraform configs [1]. I did this (including having the agent import all the initial resources from the live device), works great and is generally more robust than a script.

[1] https://github.com/terraform-routeros/terraform-provider-rou...

New comment by abound in "Words Are a Byproduct of Consciousness. For LLMs, It's Backwards"

abound — Tue, 30 Jun 2026 15:09:30 +0000

Reading it again, the book is referencing this case: https://www.theguardian.com/world/2004/jul/11/fiji.jennyfors...

New comment by abound in "Words Are a Byproduct of Consciousness. For LLMs, It's Backwards"

abound — Tue, 30 Jun 2026 14:44:19 +0000

Similarly, I'm reading "Supernormal Stimuli" now, and there's a whole section on infants raised by various animals (chimps, wolves, chickens, leopards, etc, etc). When they are found and brought back to human societies, basically none of them develop full language and integrate fully.

There's also the grim history of language deprivation experiments: https://en.wikipedia.org/wiki/Language_deprivation_experimen...

It really does seem like language is a key part of how we develop our human intelligence.

New comment by abound in "Reducing tick density along recreational trails in Ottawa, Canada"

abound — Sun, 28 Jun 2026 19:00:49 +0000

AI is not a panacea.

The interplay between different components in natural environments is impossibly complex and we basically always get this wrong. Modern LLMs might be able to surface some likely effects of altering a habitat, but it's also very dependent on humans having already studied it in some capacity, there could be new or subtle second-order (and beyond) effects that we just aren't aware of and AI doesn't have the raw data to infer correctly.

New comment by abound in "Show HN: Zanagrams"

abound — Sun, 28 Jun 2026 17:02:07 +0000

Came here to say this, Ribbit is a lot of fun, and Puzzmo in general is a really solid site.