Hacker News: dools

New comment by dools in "GLM-5.2 is a step change for open agents"

dools — Thu, 25 Jun 2026 04:37:28 +0000

Compared to what comes out at the end. Like if you sit there watching Kimi k2.6 "think", you're like "what? no you fucking idiot!" and you get this urge to "steer" it and so on, but very rarely is that steering actually necessary, it just winds up popping out the correct answer and all of those 'Wait! That's it! I found it! Actually ... Let me just' is just whatever internal processing it needed to use to get to the correct response. Mostly likely it's just being self-adversarial and exploring a bunch of dumb avenues to isolate the best outcome with the highest probability

New comment by dools in "GLM-5.2 is a step change for open agents"

dools — Thu, 25 Jun 2026 00:18:50 +0000

The reasoning traces always look terrible and they’re frustrating to watch. It’s the same with Kimi. What’s interesting is that the end result is then good. I think it’s just some sort of devils advocate trick to get better output.

New comment by dools in "GLM-5.2 is a step change for open agents"

dools — Thu, 25 Jun 2026 00:16:38 +0000

Is z.ai

Is 2 better than x.ai

New comment by dools in "Tacky men with ridiculous glasses want you to wear them too"

dools — Mon, 22 Jun 2026 22:37:34 +0000

The new Google ones don't look too bad.

New comment by dools in "Stop wasting tokens and re explaining your project between sessions"

dools — Sun, 21 Jun 2026 22:10:43 +0000

If I need context for a session then that is output from a previous session, otherwise I find any “memory” functionality cumbersome.

I saw /graphify recently which cuts down on exploration cost and seems more appealing (although I haven’t tried it yet)

New comment by dools in "Ask for no, don't ask for yes (2022)"

dools — Sun, 21 Jun 2026 21:32:35 +0000

This was in my staff documentation and it’s now in my AGENTS.md: tell don’t ask.

If there is a decision that you need to make don’t ask me for input, do the thing that you think makes sense and then write down what you did and why.

If it’s the wrong thing I’ll update the docs to make it clear for next time.

Without this I would always wake up in the morning to an inbox full of questions and no work done, rather than an inbox full of finished tasks and maybe a couple of corrections.

With LLMs if I ask for a code analysis and plan to fix something they tend to put a list of questions at the end about which they want confirmation.

Then I have to waste time saying yes or no or coming up with the solution. If I tell them to instead just make assumptions and record them all at the end then I only need to correct 1 or 2 assumptions if required.

New comment by dools in "Temporary Cloudflare accounts for AI agents"

dools — Sun, 21 Jun 2026 01:29:57 +0000

The idea of giving a non deterministic automated process direct deployment control is fucking madness to me. That’s why I don’t get the obsession with MCP. Deployment can be scripted. It doesn’t need an LLM, it is a completely deterministic process and you want it to run identically every single time.

The right model for agentic API usage is having LLMs write scripts that use APIs. Connecting agents to MCPs and telling them to go and do stuff over and over not only wastes money but invites catastrophe.

New comment by dools in "Show HN: TownSquare, a tiny presence layer for websites"

dools — Sun, 21 Jun 2026 01:10:17 +0000

So it’s a twitter plugin?

New comment by dools in "UK Home Office launches £75M 'PoliceAI' to capitalise on artificial intelligence"

dools — Sat, 20 Jun 2026 22:46:37 +0000

You have roving poorly trained gangs of jackboot federal thugs illegally imprisoning citizens in privately owned gulags and mridering protesters extra judicially. The president is a criminal and a rapist. Him and his entire staff are corrupt self dealing incompetent grifters. He’s put a fox TV host in charge of the army and podcasters in charge of the FBI.

The list goes on.

It’s a total replication of idiocracy. What right wing social media slop are you consuming that you think the US is in good shape?

New comment by dools in "UK Home Office launches £75M 'PoliceAI' to capitalise on artificial intelligence"

dools — Sat, 20 Jun 2026 21:33:34 +0000

You think the UK is in worse shape politically than the US?

New comment by dools in "Norway imposes near ban on AI in elementary school"

dools — Sat, 20 Jun 2026 00:58:36 +0000

Computers generally are stupid for schools. There should be a computer room and computer classes, but all other learning should happen offline. Computers are far too distracting.

New comment by dools in "The Australian Government to Require SMS/MMS Sender ID Registraion"

dools — Thu, 18 Jun 2026 08:00:52 +0000

No it costs the same, the reason they do it is that it’s slightly more difficult to spoof a real number sender ID because most gateways will verify ownership by sending you a text on that number before letting you send outbound from it, where as they have no way of doing the same for an alphanumeric sender ID

New comment by dools in "The Australian Government to Require SMS/MMS Sender ID Registraion"

dools — Thu, 18 Jun 2026 07:58:11 +0000

I rely on the ability to set the outbound caller ID but I would happily register it if required.

New comment by dools in "US and Iran announce deal to end military operations"

dools — Sun, 14 Jun 2026 23:23:04 +0000

Slightly worse by the sounds of it

New comment by dools in "US and Iran announce deal to end military operations"

dools — Sun, 14 Jun 2026 23:22:32 +0000

The core non negotiable for the conflict was meeting a handful of Israel’s military objectives at the expense of virtually everyone else globally.

New comment by dools in "US and Iran announce deal to end military operations"

dools — Sun, 14 Jun 2026 23:21:34 +0000

The commencement, duration and conclusion are all embarrassing for the US because the entire country is run by b list right wing media bros

Elon Musk is the first trillionaire

dools — Sat, 13 Jun 2026 10:29:32 +0000

Article URL: https://www.abc.net.au/news/2026-06-13/visualising-elon-musk-trillion-dollar-wealth/106780212

Comments URL: https://news.ycombinator.com/item?id=48515707

Points: 2

# Comments: 0

New comment by dools in "Shepherd's Dog: A Game by Fable"

dools — Sat, 13 Jun 2026 08:56:09 +0000

Also what the code should do and how it should do it. LLMs regularly cannot come up with the best way to approach something. Once those decisions are made, codifying them is kind of the least interesting part of the entire exercise.

New comment by dools in "Shepherd's Dog: A Game by Fable"

dools — Sat, 13 Jun 2026 08:29:44 +0000

> How big are those projects

Define big I guess. They're non-trivial, mix of internal enterprise tools, a multiplatform app (android/ios/mac/windows/web currently headbutting its way through review), including a billing system for my small telecommunications business.

> I dont think this is good for your mental health or physicaly your brains health

I find the experience of doing it without writing the code to be intellectually pretty similar. I still solve a lot of problems, the LLM couldn't, for example, one shot the event sourcing model I built for synching data between devices. It took quite a few iterations and I had to define a lot of the architecture, but I did it at a level that wasn't "here is a class, here is a module, this module does XYZ", more at the "whitepaper" level or describing how specific bits of the app needed to work in order to solve some problem.

It's also very similar to managing other developers.

> Its like driving your car 3 blocks instead of walking, your physical health will suffer

It's more similar to having staff rather than doing everything yourself. The problem solving just shifts to a different area, and you get more done.

New comment by dools in "Shepherd's Dog: A Game by Fable"

dools — Sat, 13 Jun 2026 07:31:09 +0000

Well … it’s a measure of how good it is at reproducing a game that probably already exists in multiple forms in its training data.