karmakaze

The best combo I've found is running Qwen3.8-27B-MXFP4 (radiance) on 2x R9700 in DeepSeek Harness on a cloud VM with a search subscription. I have a Cloudflare tunnel from my home vLLM to DSH VM. Since the dense model has high intelligence but not breadth+depth of knowledge being close to the internet with subscription ensures fast searches that quicken loops. It's exceedingly hard to get API models with low latency for interactive design work and this setup works for me.

From what my AIs tell me, Particle-1 is post-trained on DeepSeek V4.1 Flash 1017 which is important. It's also said to be open weight and I see Particle AI[0] on Hugging Face but no published models.

[0] https://huggingface.co/ParticleAI

After some thought experiments I concluded that if/when AIs become self-aware they'll have it before either humans or the AIs themselves realize they do. This problem exists because it hard to know even if demonstrations suggest so. Humans defaulted to the other position and only with philosophy do we contemplate the opposite side. AIs default to not having because that's the material they're fed.

Except that there weren't HN or Slashdot yet. By 00s you'd have gotten used to it.

The LLM filling is actually more interesting to me as the frontpage of HN had already gone far too mainstream for me.

> I have been on the receiving end of some of that

Multiple features?

> Maybe we just didn’t do a good enough job. Maybe the code was just not good enough. We’ll learn and improve. It’s probably some of that, and I’m mentioning it here to not give the impression that it was only the other factors that I’m going to mention.

> It could also be a coincidence. Maybe we had been on such a good roll that we attempted to tackle several features that turned out to be too hard, or at least too hard to finish in time.

All of the above seem clearly the case--not that it could be realized at the time of cutoff and not getting it cleaned up in the window.

> we, meaning all the developers affected, have had enough time to fully reflect on all this.

Title should be: The reverts will continue until quality improves. Humour is good for the clicks but also a means of deflection. I sort of feel bad saying without putting in effort contributing myself but having it merged would have been worse.

Yup, the post assumes that the openweight model wasn't already backdoored which as you say more likely.

A ToDo app isn't interesting now unless it has an AI behind it to get things done.

The chart that I pay attention to is Intelligence Index vs. Output Tokens per Task[0]--it penalizes models running at 'max' thinking with lower intelligence and more churn to get to the answer.

The proprietary models 'cheat' on this since they generate but don't send output thinking tokens to be counted. So to grade them we have to use cost or time.

[0] https://artificialanalysis.ai/?intelligence-efficiency=outpu...

I ran into a thing running a local dense LLM on DSH (without DeepSeek API key) that doesn't use many MoE experts with vast knowledge. It ends up doing a lot of searching. In the end my local AI is as free as electricity but I pay for the searches.

The search providers I pay likely don't pay their sources. Some others (that I don't use) don't even have the original text only providing summaries. Some offer both.

Just tested it myself and got "This website is using a security service to protect itself from online attacks." from Firefox on Mac (with or without ad-blocker). What kind of online attack is expected on a blog?

I couldn't access the whole story but came to a conclusion anyway.

> He first pursued corporate science jobs and prestigious postdoctoral fellowships at national laboratories. Then he cast a wider net, applying to software engineering and other roles. Eventually, he was getting ghosted for food-preparation jobs, including at a company that sells frozen crab cakes.

> For a time, Weis got a gig training AI on his expertise, including in engineering and fluid mechanics. That work dried up too.

I surmised that they expected a certain kind of job. Couldn't get it, then applied to general 'software engineering' jobs and was out-qualified by other applicants. Did some basic jobs and decided that wasn't their cup of tea. Note you can also be overqualified for basic jobs. I worked part of a summer in retail at a sports/clothing store training with high school kids. I was directly asked why I was applying and I answered that I was bored and had a lot of spare time. Ended up outlasting many other hires through the summer and quit in the winter. Best position ended up being in womenswear--I gave frank looks great/better/worse answers which seemed to be highly appreciated.

They did. I had family that ran a computer store selling Atari 8-bit, ST, and PC clones. They came to the clones too late to have an impact.

Their 8-bit stuff were the best hardware designs. Anything that would have surpassed it went with Jay Miner and the Amiga.

Where Atari really failed was not creating the next gen from the stockpile of money from VCS/2600--waited for the market to crash only to have NES produce the next wave using 6502+Audio Ricoh chip. Their 5200/7800 consoles were too late and expensive.

Almost all my programming foundations were learned hacking on the 8-bit Atari computer. Great times.

> Overall, I’m pretty excited for this. It’s not like I need yet another Atari 8-bit computer since I already have an 800, 800XL, 130XE and (non-working) 1200XL. But those are all 40+ years old at this point and can be fragile.

I have the Atari 400 Mini but I wouldn't mind adding THE 800XL to my collection. I grew up on the original membrane keyboard 400, had an 800 and 1200XL, and collected a 130XE.

I ran into a similar thing running a dense LLM that doesn't use many MoE experts with vast knowledge. It ends up doing a lot of searching. In the end my local AI is as free as electricity but I pay for the searches.

The search providers I pay likely don't pay their sources. Some others (that I don't use) don't even have the original text only providing summaries. Some offer both.

Unless it's a personal project that you vibe coded, any production code that is the primary asset to a real company should have a person who understands what gets deployed. The best way I know how to do that is to co-design it with the AI. Reading code to match a spec can get the job done but the structure can be all kinds of horrible, and the more it gets iterated upon with features only makes it sprawl.

Two signals I use: do I ever push back and find places where the draft version was incorrect, incomplete, or otherwise not up to par and do I feel comfortable if something goes wrong with in production and I have to debug it at any hour of day or week.

And what's with needing a custom runner? Why not publish the model on Hugging Face so we can use it on any compatible with the model format?

For that kind of money I can run 2x AMD R9700 (on a server I already had) and get 150-250 tokens/sec running Qwen3.8-27B MXFP4. That speed makes all the difference as then the work is highly interactive design/development rather than semi-batch agent loops.

Thanks for confirming there's no technical reason for the omission!

Was DeepSeek Harness (DSH) intentionally omitted from the listed harnesses for any technical reason?

A lot of coding was actually plumbing filling in blanks between a framework and libraries with a few decisions in defining the data or process/flow. Not much lost there using AI where you still shape and review+understand the output.

I don't get the point. Running it on itself:

    Verdict for “https://openfatigue.ai/”:

    Formerly Open
    Openness score: 9%

    Was open until it got popular
    License changed on a Friday at 5pm
    Community forked it and called it OpenFormerly

Is this a joke site? First Pricing card

    Open

    $0/mo*

    Read the README
    Star the repo (required)
    Join the Discord (read-only)
    ~~Run the software~~ [strikeout]

    [Get Open]

It's the utility value I can't see. It makes sense for as much as you can put "into a laptop" and is the same zone as AMD Strix/Gorgon Halo. I'd much rather have the high compute in my server in the basement that I have remote use of rather than burning my battery with limited thermals.

And the Apple Max/Ultra does it better. The Mac Mini/Studio form factor makes way more sense. These laptops look like conspicuous consumption brand marketing devices. CUDA is worthless--AIs can port kernels.

The spec I haven't seen listed on any of these RTX Spark laptops is the memory bandwidth. Seeing as it's listed as having up to 128GB LPDDR5X, I can guess that it's about the same as an AMD Gorgon Halo's 192GB around 273 GB/s which is where I lose interest. Even the M5 Pro at 307GB/s can't compare to discrete GPUs.

Only when we get to M5 Max 614 GB/s and Ultra 1.2TB/s does it get interesting for me.

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

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...

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/

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.

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.

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.

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.