Hacker News: sieste

1931 China Floods

sieste — Fri, 28 Aug 2026 13:28:18 +0000

Article URL: https://en.wikipedia.org/wiki/1931_China_floods

Comments URL: https://news.ycombinator.com/item?id=49478168

Points: 2

# Comments: 0

New comment by sieste in "fx :Tiny, open, native coding agent."

sieste — Thu, 20 Aug 2026 14:08:25 +0000

For people working with small local models like Qwen 35b what's even more important us that the LLM is good at coding in the language in which the agent harness is written so that it can write skills. I really like pi but had a few instances now where Qwen wasn't able to extend it because it isn't very good at writing typescript. Does that sound familiar to anyone, and did you find any fixes?

New comment by sieste in "Midlife Vascular Risk Burden and Dementia-Free Survival Years"

sieste — Mon, 10 Aug 2026 20:49:07 +0000

The couch to 5k programme is now routinely recommended by GPs in the UK (and elsewhere), a very positive development in health care in my opinion.

https://www.nhs.uk/better-health/get-active/get-running-with...

UK wants datacenters to pay a fee for grid connection requests

sieste — Thu, 06 Aug 2026 13:10:04 +0000

Article URL: https://www.theregister.com/systems/2026/07/31/uk-wants-datacenters-to-pay-a-fee-for-grid-connection-requests/5281248

Comments URL: https://news.ycombinator.com/item?id=49196189

Points: 5

# Comments: 1

New comment by sieste in "Teaching Kids Forth"

sieste — Mon, 27 Jul 2026 05:23:15 +0000

> I wanted to avoid teaching syntax. While Python makes sense as pseudocode [...] it is still nearly incomprehensible to new learners [...] I decided I wanted to either teach Forth or Haskell.

Sorry but this reads like a joke. If you find python incomprehensible, Forth and Haskell won't even register as languages.

New comment by sieste in "Qwen 3.8"

sieste — Sun, 19 Jul 2026 12:14:43 +0000

What is a "credit" and how does it translate to tokens for the different models?

Collapse of AMOC ocean current may be locked in

sieste — Tue, 07 Jul 2026 08:34:02 +0000

Article URL: https://institutions.newscientist.com/article/2533017-collapse-of-amoc-ocean-current-may-already-be-locked-in/

Comments URL: https://news.ycombinator.com/item?id=48815076

Points: 6

# Comments: 0

New comment by sieste in "CERN bids farewell to the LHC and enters Long Shutdown 3"

sieste — Wed, 01 Jul 2026 07:58:18 +0000

I treat these nutjob articles as a subgenre of science fiction and when they're somewhat well written find them very entertaining. The author cosplaying investigative journalist, one part of the audience acting as if it's a real discovery and another part playing debunking and outrage, is all part of the performance and it's hilarious. Check out the flat earth movement, it's great entertainment all around!

University of Exeter to cut 150 academic staff

sieste — Wed, 24 Jun 2026 21:42:45 +0000

Article URL: https://www.bbc.co.uk/news/articles/cx2djnz3y47o

Comments URL: https://news.ycombinator.com/item?id=48665972

Points: 6

# Comments: 0

New comment by sieste in "Dirty Little Zine – a tool for making an 8 page printable Zine"

sieste — Wed, 24 Jun 2026 06:19:24 +0000

The zine enthusiasts in this thread might enjoy this little tool I made to print out and zine-fold Project Gutenberg books: https://github.com/sieste/pocketbook

New comment by sieste in "Show HN: Are You in the Weights?"

sieste — Thu, 18 Jun 2026 21:36:45 +0000

German football goalkeeper here :)

New comment by sieste in "Running local models is good now"

sieste — Wed, 17 Jun 2026 09:22:19 +0000

I'd love for European countries to embrace their priorities around people and environment and train a model on public domain data that can run efficiently on cheap hardware. Redefine benchmarks around these ideals and optimise towards them, rather than trying to enter a race that you can't possibly win and didn't want to run in the first place.

New comment by sieste in "Running local models is good now"

sieste — Wed, 17 Jun 2026 08:03:58 +0000

The "middle powers" (cf Carney) should invest in local models, rather than relying on US and China allowing them to rent their AI models. It takes a single executive order to cut the rest of the world off of American AI tools. "I'm happy to pay whatever to rent frontier models from hyperscalers" makes sense if you're citizen of a superpower, but it's risky, naive, bordering on irresponsible to adopt this mindset otherwise, especially when your business or career depend on the tool.

New comment by sieste in "RTX 5080 and RTX 3090 Setup: 80 Tok/s on Qwen 3.6 27B Q8"

sieste — Sun, 14 Jun 2026 16:57:21 +0000

Imagine how accurate you could be if you could circumvent the coding agent and just type the source code directly into an editor all by yourself o_O Like a write_file skill but for humans!!!

New comment by sieste in "RTX 5080 and RTX 3090 Setup: 80 Tok/s on Qwen 3.6 27B Q8"

sieste — Sat, 13 Jun 2026 15:56:27 +0000

That's almost exactly my setup and I'm very happy with its performance.

I noticed recently that I started to prefer my local Qwen3.6 35B A3B and pi agent over Claude Code.

Both fail at different tasks, and Qwen more so than Claude.

But the way Qwen fails is much more straightforward. In writing tasks Qwens hallucinations and bullshitting are much easier to spot because it doesn't have the sleek vocabulary and wordsmithing skills to disguise its ignorance.

In coding tasks that Qwen can't solve it often just goes into a tool calling doom loop that the pi harness can catch, whereas Claude attempts ever more convoluted and creative things just making more and more mess that takes forever to clean up.

I think part of the story is that the tasks for which I use AI are fairly simple and maybe don't need a frontier model. But I wonder if "proper" developers had similar experience?

Scientists found the optimal robot body, and it has 20 legs

sieste — Fri, 29 May 2026 21:36:42 +0000

Article URL: https://www.livescience.com/technology/robotics/scientists-found-the-optimal-robot-body-and-it-has-20-legs-watch-it-scale-walls-and-move-through-trees

Comments URL: https://news.ycombinator.com/item?id=48329638

Points: 5

# Comments: 0

New comment by sieste in "Investigating how prompt politeness affects LLM accuracy (2025)"

sieste — Thu, 28 May 2026 15:34:00 +0000

I have a different approach. Just treat all LLM queries as what they are, instructions to a computer program to generate a desired output. Neither niceties nor insults make a qualitative difference, so you might as well just skip them altogether.

It's a bit as if shell commands added im/politeness arguments that do nothing other than making you feel better about the interaction, like

    git pull --please

    ls --forthemillionthtime

I wouldn't use those either.

New comment by sieste in "Germany news: Childfree adults to pay more for elder care"

sieste — Tue, 26 May 2026 16:10:23 +0000

This is very cruel towards people who want to have children but can't.

Running creative online bots with ten thousand followers

sieste — Thu, 30 Apr 2026 20:50:18 +0000

Article URL: https://stefanbohacek.com/blog/on-running-creative-online-bots-with-ten-thousand-followers/

Comments URL: https://news.ycombinator.com/item?id=47968052

Points: 4

# Comments: 0

New comment by sieste in "An AI agent deleted our production database. The agent's confession is below"

sieste — Sun, 26 Apr 2026 19:54:45 +0000

Good point, it's like having an instruction "Never fucking output a token just because it's the one most likely to occur next!!1!"