Hacker News: gb2d_hn

New comment by gb2d_hn in "Herdr has released native app"

gb2d_hn — Fri, 30 Oct 2026 13:27:40 +0000

Had a play with the native app - it's a complete new set of keyboard shortcuts from the TUI. Don't really see the advantage.

New comment by gb2d_hn in "Herdr has released native app"

gb2d_hn — Fri, 30 Oct 2026 10:25:39 +0000

Yeah that copy is pretty bad. My understanding (someone correct me if I'm wrong), but the herdr native app is an improvement over the existing TUI multiplexer, with a new API for facilitating comms between agents. Herdr is really useful if you've not tried it. I'll be giving this a go (I hadn't really been using agent comms between panes anyway, more just for workspace navigation). Seems you can think of herdr as a 'harness for your harnesses'!

New comment by gb2d_hn in "Switzerland. Block by block. At 1:1 scale"

gb2d_hn — Mon, 26 Oct 2026 10:08:12 +0000

Why would I buy a potato when I could grow one myself. Why do I give a busker money when I could play the real track on spotify. Why do we give anyone any money? Why don't we just do everything ourselves?

New comment by gb2d_hn in "There's never been a better time to go into math (by: 3blue1brown) [video]"

gb2d_hn — Sun, 25 Oct 2026 14:16:44 +0000

Your friends quote is so true. There's too many thin stories with empty padding around them to make an idea a novel!

New comment by gb2d_hn in "Challenge Is Gone"

gb2d_hn — Sun, 25 Oct 2026 14:06:30 +0000

Currently, for me the challenge has gone from can I build it, to can I build this and everything else I need, and structure it to be maintainable for the long term, so I can keep stacking bricks. This has found me leaning harder into IaC, use of and contribution to open source (for secure ownership, longevity of system and cost reduction) and structuring the development tooling around agents. That will be an ongoing process, but I feel that I'm at the point where I can move onto building what matters. I've already built a few of the tools I've dreamed of having for years (there's a couple of rough edges but it beats the tools I had before), and I think, like the author this will free me up to stay on the next step (building what matters) for good.

New comment by gb2d_hn in "There's never been a better time to go into math (by: 3blue1brown) [video]"

gb2d_hn — Mon, 19 Oct 2026 15:38:07 +0000

There's a couple in that collection - 'Understand' is about a brain injury patient that gets an experimental treatment and becomes super intelligent - what he does with that intelligence and humanities attempts to restrain him, and 'Division by Zero' is a mathematicians struggle to continue with life when a discovery undermines all of mathematics. It's a great collection.

New comment by gb2d_hn in "There's never been a better time to go into math (by: 3blue1brown) [video]"

gb2d_hn — Mon, 19 Oct 2026 15:32:11 +0000

I'm ashamed to say I've started both of these and not managed to finish :) I will try again (kiddo's tire me out and means Ted Chaings short stories are perfect!)

New comment by gb2d_hn in "There's never been a better time to go into math (by: 3blue1brown) [video]"

gb2d_hn — Mon, 19 Oct 2026 10:49:04 +0000

As I commented in another thread: I just finished a very short story by Ted Chiang - 'The evolution of Human science' it starts at the point where it's 25 years since humans contributed a scientific paper because 'meta humans' now handle all research, and communicate digitally such that humans can only get a low fidelity report of what the agents actually know, and the endeavour to understand has become like a best effort archeological like hobby for interested humans. The story assumes that the 'meta humans' will always act in humans best interests. I believe it's from 2002, it's incredibly precient (The stories of your life and others is the collection the story is in. Many of them are very relevant to modern AI actually).

New comment by gb2d_hn in "How employment is changing at Anthropic"

gb2d_hn — Mon, 19 Oct 2026 09:51:26 +0000

You can solve problems empirically, but you can never guarantee you've hit all the edge cases the original code did. That's fine for non-mission critical systems, but would you be ok with your passenger jet onboard systems having been rebuilt from empirical observations?

New comment by gb2d_hn in "How employment is changing at Anthropic"

gb2d_hn — Mon, 19 Oct 2026 09:44:06 +0000

I think the difference is whether agent availability in the future is guaranteed. I agree that no one had the whole picture before, but at least theoretically you could replace x employees with another workforce who in time could be expected to match the understanding and output of the original workforce. With agents, if capability is consolidated with a single organisation and that organisation changes it's terms of business, you cannot replace the army of AGI-agents with a human workforce. It's a single and total point of failure.

New comment by gb2d_hn in "How employment is changing at Anthropic"

gb2d_hn — Mon, 19 Oct 2026 07:23:16 +0000

Thank you, I'll try and find those.

New comment by gb2d_hn in "How employment is changing at Anthropic"

gb2d_hn — Mon, 19 Oct 2026 07:22:44 +0000

I think this could be summarised as alignment being conflated with intelligence - i.e. what seems unintelligent to some is just misalignment with their own values.

New comment by gb2d_hn in "How employment is changing at Anthropic"

gb2d_hn — Sun, 18 Oct 2026 11:46:59 +0000

This just can't be sustainable. Ever increasing agent activity can only move to the point where it's literally impossible for humans to have a collective awareness of how the systems that support our lives actually work. How does anyone think this is going to end well? If as humans we loose control of vital systems, when they stop working one day (and they so easily could unless the agents are perfect and 100pct aligned with the general good of humanity (how do we even define that)) we could find ourselves without the ability to run healthcare systems and power grids, that have evolved so much such complexity that no human can intervene to fix them. I do believe that you can create feed back loops where probabilistic agents can be used to create deterministic checks and balances, and solve real problems for good. But it's a wild west at the moment and that is not what's happening in so many companies, and the solutions are not yet on the horizon. Even if the 'agents can handle it' ... where does that leave us? Unable to run our societies without puting everything through frontier LLMs? I just finished a very short story by Ted Chiang - 'The evolution of Human science' it starts at the point where it's 25 years since humans contributed a scientific paper because 'meta humans' now handle all research, and communicate digitally such that humans can only get a low fidelity report of what the agents actually know, and the endeavour to understand has become like a best effort archeological like hobby for interested humans. The story assumes that the 'meta humans' will always act in humans best interests. I believe it's from 2002, it's incredibly precient (The stories of your life and others is the collection the story is in. Many of them are very relevant to modern AI actually).

Show HN: Agent Chat in Your Markdown Notes – Chat with Context and Save Response

gb2d_hn — Fri, 16 Oct 2026 15:53:13 +0000

EtherPK now has Agent Chat.

I use AI agents in two distinct ways. For coding I use TUIs, but for day-to-day and non code projects I used to use the web chat UIs like many others. Two things about this was always jarring:

You're starting context from scratch. You might have a couple of agent instructions configured, but you have to tell the agent what you're thinking, from the beginning. When you get the information you need, holding on to it is hard. Within a day or two it's burried in your chat history. EtherPK is a mardown based PKMS (notes app), and it solves both of these problems.

You can type /Agent within your notes (EtherPK supports standard prose and outliner blocks in the same document). The Agent Chat panel opens within your document, and you can choose how much context to give it. That might be nothing, the current block tree, the document or the whole graph (in the case of the latter - immediate surounding context is sent and the agent is given tools to navigate the rest of your graph). You control what the agent gets, and what stays private.

Comments URL: https://news.ycombinator.com/item?id=50119958

Points: 1

# Comments: 0

Show HN: Link and visualise places in your notes with Markdown and wikilinks

gb2d_hn — Tue, 13 Oct 2026 12:35:09 +0000

EtherPK (our markdown and wikilink based PKMS) now has maps. Lots of the concepts in a PKMS relate to places in the physical world, and for me that's often trips and travel. For example, I keep a list of places I've loved camping, and I often drop a note in my journal about a particular campsite with the [[Campsite]] wikilink. The backlinks for [[Campsite]] already show me every document where I've mentioned one. Now each of those notes can hold a map too, with pins and routes that I place by hand or find by postcode, ZIP code or place name. The Map View then gathers the places by concept. The Map View for [[Campsite]] shows every campsite I've noted on one map, framed to fit them all. (There's no picture of that one, because those places are too special to share here!)

Comments URL: https://news.ycombinator.com/item?id=50070683

Points: 1

# Comments: 0

New comment by gb2d_hn in "Discover vibe-coded alternatives to popular software"

gb2d_hn — Tue, 13 Oct 2026 08:40:41 +0000

:) "Well, this little maneuver's gonna cost us 51 years!"

New comment by gb2d_hn in "Discover vibe-coded alternatives to popular software"

gb2d_hn — Mon, 12 Oct 2026 15:59:56 +0000

I'm not saying you can't develop good agent assisted code, you can. but on aggregate, this directory is unlikely to be a trove of great apps.

New comment by gb2d_hn in "Attack of the Vibe Coded Photoshop Clones"

gb2d_hn — Mon, 12 Oct 2026 07:18:27 +0000

LGTM (think this video captures the vibe well https://youtu.be/3TNpOD6bov8?is=X9kLvF9WyWHb-slu)

Show HN: EtherPK – an Obsidian and Logseq alternative with prose and blocks

gb2d_hn — Mon, 05 Oct 2026 14:11:18 +0000

EtherPK allows for prose and blocks in the same docs, and has static site publishing, so you can maintain your outline style notes with your blogs and docs. For more features: https://www.etherpk.com

Comments URL: https://news.ycombinator.com/item?id=49965142

Points: 5

# Comments: 0

Show HN: EtherPK – a notes app where any concept is a Kanban Board (from tasks)