HNHacker News
TopNewBestAskShowJobs

karmakaze

9,326 karma · joined April 23, 2012

submissionscomments
karmakaze··on Ask HN: Whats the first command you run on a new server?
Who, what, when, where, how, am I?

    whoami
    uname -a; cat /etc/issue
    date
    pwd; curl http://ipv4.icanhazip.com
    df -h; free -h; # htop
karmakaze··on Web Search API
I later discovered SerpBase[0] which has even lower pricing but perhaps not as fast or reliable. Might check it out when I use up all my balance.

[0] https://serpbase.dev/blog/serpbase-vs-serper-dev-serp-api-pr...

karmakaze··on Mastering SIMD with Java Vector API
If you need SIMD for new project work, I would consider Mojo[0] as it's v1.1 already. If you're unfamiliar its creator also made LLVM, Clang, and Swift.

[0] https://mojolang.org/docs/std/simd/SIMD/

karmakaze··on Ask HN: What Is Your Personal Backup Methods
For personal files/media, I heard about the 3-2-1 method: 3 copies, 2 formats, 1 offsite. I'd likely want to add a complete self-contained toolchain to convert format with that offsite copy.

I'm not nearly as particular with my OS backups as I used to be. For instance Desktop personalization is minimal. I've used too many computers over the years to maintain much configuration beyond a small number of dot-files. Hobby code goes in Github/codeberg.org and some kind of cloud sync for my daily driver.

Another thing that ended up happening naturally is that I keep hard drives of old computers when I upgrade. They serve as point-in-time snapshots. I haven't made it a point to be able to necessarily read all of them but it doesn't take much like having a number of USB-disk/media interface adapters around.

karmakaze··on Reasons to Dislike AI Coding
I was curious about codeberg.org as an alternative to Github for opensource work. They had voted on an LLM policy and decided against vibe-coded repos while allowing some AI use. This got me thinking how I want to use AI and if it fit with their policy.

The best I could figure is that I like to start with requirements, use AI to discuss and settle on its high level design and specific aspects of its implementation. I may or may not read all the code, but the key thing is even if I didn't read the code in advance, doing so would not be a surprise and I'd know what it was doing and how it was doing it because those were things I decided during the up-front conversations and not left as an open exercise for the AI. And coming back to the codeberg.org vote I can guess that it was elements like these that they wanted to guard. They don't want repos whose owners don't know what the code does in a technical sense or how it's constructed etc. There's likely other things too like seeing text that doesn't read like people wrote it and I find that tiring to read (in a literal way, I get drained from reading too much of it) and endorse minimizing that.

Another thought was that my ever long search for better and better programming languages was that if I have a clear vision of what I want the language should have the least friction to write it down. Some languages that feel closer than others were Elm, Elixir, F#/OCaml, Pony, Rust, Kotlin, Go. Only a couple of these are my languages I'd regularly used but would prefer to have my AIs write in them. For web I'd probably also accept Vue, Svelte, or (simple) React. In particular using Go for mini back-ends is particularly effective as the coding style tends to be regular and boring which minimizes differences between human and machine written styles. So in a sense giving specs at multiple levels of abstraction and detail is the perfect high level language I'd been wanting.

karmakaze··on Anthropic reported diary entry to police, woman faces felony charge
I don't think it qualifies for this part:

> The communication must be made in a manner in which another person may view it.

Even 'transmitted' is too broad if you also consider iCloud backup to be a means.

karmakaze··on Hacker News addiction and taking simple mundane breaks in life
The high volume of posts (and corresponding lower signal quality) cured me. Now I visit see a handful of stories that I didn't need to read. Occasionally worthwhile so still visit but not frequently like I used to.
karmakaze··on Web Search API
Can Gemini Flash Lite 2.5 be made to return raw search results. Some 'search' providers I looked at returned summaries, or vector relevance matches (of presumably a smaller/stale page set).
karmakaze··on Web Search API
I was just looking into these as DeepSeek Harness w/ Qwen3.8-27B relies heavily on search. I was going to go with Serper.dev[0] $1 per 1000 (or lower in quantity).

The providers[1] behind this Web Search API have very different rates:

    Ceramic.ai: $0.25 per 1,000 requests
    Linkup:     $5.00 per 1,000 requests
    Exa:        $7.00 per 1,000 requests
[0] https://serper.dev/

[1] https://developers.cloudflare.com/web-search/providers/

karmakaze··on Micro Center requires photo ID and signed no-export pledge to buy gaming GPU
A $5000 GPU with a TDP of 575W isn't the kind of thing that goes in a typical "Gaming PC". I love that it exists though. Can't wait for AMD to release a competitor and get some sane pricing (if AI demand for wafers levels off).
karmakaze··on Muse Gadgets
It says make it your own. Then

> Gadgets you build with the Muse Gadget SDK need a token. Add it to your SDK configuration so your gadgets can pair with the Muse app.

> Each token can be used by a limited number of devices.

> The Muse Gadget SDK is intended for personal tinkering and is not a supported product or developer platform. The SDK can change, break, or stop functioning without warning.

Doesn't really feel like it's my own.

karmakaze··on An open letter to Scott Alexander
The first (quoted) tweet says "Is Al really going to kill us all? The scenarios are preposterous, and the presumption of inevitability encourages fatalism, panic, and distraction from the more mundane and realistic safety challenges."

This in itself I find problematic. Solving the mundane and realistic safety challenges are what prevents the potential (preposterous) outcomes. There's no need to ignore anything other than the sensationalism like anthropomorphising. The Paperclip Maximizer is meant to be an exaggerated thought experiment where an AI doesn't actually "want" anything, it's "literally doing" what it's supposed to. It's surprising that Pinker doesn't seem to see that, or sees it and doesn't believe no version of it is possible.

Construction machinery doesn't need to be alive to kill you--just left running unattended.

The difference is that AI doesn't have a well bounded construction site.

karmakaze··on Rails and AI
And magical action at a distance. No thanks.
karmakaze··on Python Workers are now generally available
They should support Mojo which might be a great fit for edge compute.
karmakaze··on M5 Ultra Mac Studio Review
I really appreciate seeing these dense model numbers. For a large unified memory system though I expect that MoE numbers are what people are more interested in.

These numbers could and should get much better. As an example I can run Qwen3.8-27B-MXFP4 (W4A8) on 2x AMD R9700 that gets 260+ tokens/sec to start and slows down to ~110 tokens/sec over 128k context and can do the max 256k. These are for batch size 1 and throughput goes higher with batching. This is due to speculative decoding, efficient all-reduce inter-gpu compression, and custom GEMM kernels for the specific hardware. Note each R9700 only has 644 GB/s memory bandwidth.

karmakaze··on Ask HN: How do you interview devs in a post-AI world?
Basically the same as always--an extended interactive Turing test. Can they speak coherently and in-depth about the things they claim to have done on their CV/resume?
karmakaze··on Goose: 1.16x faster than C++ and 1.12x than safe Rust, while memory safe
Cluould be viewed like a fancy evoultion of CHICKEN (Cheney on the MTA) that used stack for everything.
karmakaze··on Can we stop with the uptime percentages?
Mentally convert to downtime: 99.8 is clearly twice as bad as 99.9

Similar for LLM measures from an ideal 1.0 mark.

karmakaze··on Microsoft says AI rival Anthropic could have 'disastrous impact' on humanity
The whole story is a joke--Microsoft has AI?

Apparently they're cooking up MAI (Microsoft AI), and I'd seen their small Phi models listed online. Calling Anthropic a competitor is hilarious.

karmakaze··on Salesforce Global Outage
Yup. Could be that everyone was rushing to get all their products and demos ready leading up to it.
karmakaze··on AI is breaking our proxies for expertise
> i.e. whether frontier AI models aren’t generating or can’t generate new mathematical ideas. [...] I give basically zero credence to the idea that AIs are incapable of this because of some intrinsic feature of how LLMs work.

I also believe there are limitations of LLMs, but not necessarily where people think. I won't expect LLMs to be creative solvers until they can tell a novel funny joke with any recognition/consistency.

karmakaze··on People who can't picture anything are rewriting the science of imagination
Yes. Reminds me of "Poetry is the art of giving different names to the same thing" vs "Mathematics is the art of giving the same name to different things" -- Henri Poincaré. Set of spacial facts is what's left when all the incidental embellishments are removed--pure abstraction.
karmakaze··on Anecdotally, programmers dislike "reduce"
It's part of the functional trio: map, filter, reduce--and half of MapReduce.
karmakaze··on Unsolved Problem by Fields Medalist Breached by Two High School Students
Difference being anyone can be a "script kiddie". I don't think anyone could direct an AI to proofs like this one.
karmakaze··on People who can't picture anything are rewriting the science of imagination
I've also had this kind of topological knowingness which I couldn't name. Another comment here says "schematic conceptual" which captures what it feels like for me.

Another good explanation here is that it's all taking place but that last step of creating the visual is suppressed (as intended) while conscious as that would be hallucinating.

karmakaze··on HP ZGX Fury Is Now Orderable: GB300 Superchip, 748GB Unified Memory
This is a bundle where you end up paying for parts that aren't as useful:

    - 252 GB HBM3e VRAM
    - 496 GB LPDDR5X RAM
I would rather have a system using 2x Instinct MI350P GPUs (288GB total) for much less.
karmakaze··on Ask HN: What default model do you use and why?
Personally I'm using Qwen3.8-27B (MXFP4 quant W4A8) locally hosted on a pair of AMD GPUs (with DeepSeek Harness). It starts at 250 tokens/sec down to 120 past 128k context.

At work mostly Opus 4.8 (sometimes a GPT or Gemini 3.1 Pro). I find Opus 5 chatty/slower and Fable can venture into over-engineering itself into unnecessary complications.

karmakaze··on Busabase for DeepSeek Harness: An Agent database that runs apps and skills
Busabase[0]

> Languages: TypeScript 98.4%, Other 1.6%

Not for me.

[0] https://github.com/busabase/busabase

karmakaze··on I think I hate the internet
Seems like a random rant to me.

> What is the internet now to me? In many ways it’s something that I have to tolerate to do many things that functioned fine before. I have to use an app to pay for parking. I need to create an online account to pay for a family swim at the local leisure centre. I have to submit an online form to book a slot at the local recycling centre. I need an app to check my bank and credit card balances.

It's so much more annoying to do any of these things without/before internet. I don't do half of the other things in the rest of that paragraph. Like for phones I just get a used CAD$400 Android phone with good audio output.

karmakaze··on The Navier–Stokes Millennium Prize Problem
I think it's largely due to psychology. If 210m is considered the best, then as they approach it they may start to tense up and choke. When the goal and possibility is known as 500m, then there's no point being concerned near 210m.
← PreviousPage 2 of 34Next →