HNHacker News
TopNewBestAskShowJobs

lelandbatey

4,175 karma · joined July 10, 2012

I'm Leland Batey. I make things for the internet. I'm here: http://lelandbatey.com/
submissionscomments
lelandbatey··on Going Dark, and the era of law enforcement hacking
Read the article. That's what the article says.

> Thus: over the next two years, major pieces of software are likely to run out of remotely-exploitable bugs.

> While I think this is great, for law enforcement and offensive intelligence agencies, it’s going to be a nightmare.

> So what do we do about it? I honestly have no idea. [...] it’s just occurring to me that we’re on a long greasy slide to a place that will look different than where we are today. [We’re] just going to have to hope that this time we make the right choices.

lelandbatey··on Qwen 3.8 27B
I can get 128k context on a 5070ti with 16 GB of VRAM (using the Unsloth 2-bit quant[0]). This is via a .bat file on Windows 11. I'm getting about 50-60 tokens/second and the quality is much higher than Qwen 3.6 27B. I'm using llama.cpp[1]:

    llama-server.exe ^
        -m "Qwen3.8-27B-UD-Q2_K_XL.gguf" ^
        --presence-penalty 0.0 ^
        --repeat-penalty 1.0 ^
        --fit-ctx 128000 ^
        -ctk q4 0 ^
        -ctv q4 0 ^
        --reasoning-budget -1 ^
        --chat-template-kwargs "{\"preserve thinking\": true}" ^
        --host 0.0.0.0 ^
        --port 8033
[0] https://huggingface.co/unsloth/Qwen3.8-27B-GGUF (UD-Q2_K_XL)

[1] https://github.com/ggml-org/llama.cpp/releases

Instructions if you want to do the same:

1. download two files llama-b10434-bin-win-cuda-13.3-x64.zip and cudart-llama-bin-win-cuda-13.3-x64.zip from that llama.cpp Github releases page, and extract both into the same folder.

2. Download the Qwen3.8-27B-UD-Q2_K_XL.gguf file from huggingface and put it into the same folder beside the `llama-server.exe`.

3. Create a file named "RUN_QWEN_3.8.bat" next to `llama-server.exe` and put the text above into that bat file. Double-click the bat file, then open http://localhost:8033 in your browser to see a chat window.

You can use it with any agents by pointing them at http://localhost:8033/v1 which is a working OpenAI compatible endpoint (it doesn't use a token, if you give one it's ignored).

Congratulations, you're now running Qwen 3.8 27B.

Note: I built the computer in question for playing games, yes it needed to be Windows 11 for anticheat reasons to play games with family, I didn't want to dual boot so here I am. I figure I should share instructions for folks who may also have a Windows PC around for such purposes. Specs for this are AMD 9800X3D, 32GB of system RAM, RTX 5070Ti 16GB

lelandbatey··on Grok Bot
Yes, you e always been able to do this, as long as you get an actual contract that's enforceable.

The thing about most sites is they're public and you don't need to sign a real contract to use them. Can't have it both ways.

lelandbatey··on Crime Pays but Botany Doesn't
You've done a great job with the "how big does it get"/"what will it look like" SVG diagrams, those are incredibly helpful.

https://indigene.app/plants/symphyotrichum-subspicatum

https://indigene.app/plants/juncus-patens

Very helpful for choosing plants.

lelandbatey··on Increasing the lifespan of a bulb makes it worse in every other way
Yep, I have a 15 year old LED lightbulb that's a "60 watt equivalent" and it works great. It was one of the first LED bulbs I bought, and I only bought one because I remember it costing individually about $25, maybe more. It's got a very heavy metal heatsink where nowadays you have just a plastic "neck" of the bulb. It chugs along wonderfully (though the color is noticable a little bit greener than later cheaper bulbs that have better color accuracy).
lelandbatey··on Passkeys were invented by engineers with zero understanding of consumer brain
> This makes it impossible to copy and paste your passkey to the wrong person (someone trying to trick you).

It also, unfortunately, means it's not possible (via most passkey implementations) to back those passkeys up to paper. Which is quite unfortunate: backing up to paper is one of the most stable and human accessible ways of ensuring redundancy and continuity, an inevitable but also oft-ignored part of credential management.

Security folks would like to pretend "solving continuity" isn't a problem, or is a problem that doesn't need to be accessible.

lelandbatey··on I tricked Claude into leaking your deepest, darkest secrets
The point is to not give every user (especially the LLM user) sudo access.
lelandbatey··on An agent in 100 lines of Lisp
By my eye it's not that different, it's riffing in it from a Lisp perspective.

It's pretty amazing to write your own agent BTW. I've got a zero-dependency all-in-one-file agent harness I wrote myself. I use it all the time now because I can get it from anywhere and I can know EXACTLY what it'll do (as much as you can with any model), what it's been told vs not. Using it as a harness for models I'm hosting myself makes me feel like some kind of LLM homesteader: it's a set of tools I'll always have that will only change as much as I want it to change.

lelandbatey··on Price per 1M tokens is meaningless
I was a student whenever I wrote my old bios but I've been a developer professionally for over 10 years at this point.

My inspiration was the mayor idea from Gastown, plus wanting to formalize the informal workflow I used with agents and Jira at $dayjob.

lelandbatey··on Price per 1M tokens is meaningless
Yes, it's a "cloud provider" but it's a cloud provider running an open model you can download (and that other cloud providers do host). I just happen to not have a computer big enough to host it.

As for the Orchestrator, it's pretty simple. In essence, it's like "Jira/Trello/Kanban on autopilot". Work items have states, a state machine defines how those work items transition between states, states are todo, in progress, retrying, reviewing, code reviewing, done. work items also have connections, allowing the LLMs to specify a dependency graph, and the dependency graph informs the dispatch order/parallelism, as well as when branches have to be merged. I talk to the steward, the steward has tool calls for interacting with all the data, and the orchestrator auto-dispatches all the work that comes in. I can generate work as fast as I can describe it to the steward, and that's usually the bottleneck.

So far I haven't had to deal with "how do you get the LLM to re-organize the work mid flight due to a worker finding something not accounted for by the planning", but I assume it'll come soon. The most complicated digraph I've tossed at it was 9 items and 4 layers deep. The kind of work I've given it hasn't been scoped large enough yet, so we'll see how it tackles that.

lelandbatey··on Price per 1M tokens is meaningless
Have you been using those models? I've been using a hand-rolled orchestrator with Mimo v2.5 (I seem to be paying $0.017 per million/tokens after their heavy caching) and it's been very impressive. I started with it in Opencode as a harness, then had it build its own micro-harness with stdlib-only Python, then used that to build a local stdlib-only Orchestrator with CLI and web harness, and now I'm using that for improving itself and now multi-project wider-ranging software. I talk to a steward who investigates and plans, then the plans are handed off to parallel worker agents who go through a work, test, interrogate, review, eval state machine for quality (all autonomously) with me at the end just reviewing the work or getting notified if the work items aren't progressing due to the workers getting stuck. So far the only "getting stuck" has been bugs/configs on my part, all at a pretty great quality bar, and at a price that makes me laugh at things like Opus.

I'm still using Claude at work (they're the only approved provider), but wow are the smaller models starting to SMOKE the big ones. At this point, all I'd consider paying out of my own pocket for is the lowest-limit Anthropic/GPT plan to get a big model as the Steward, but I wouldn't pay for ANY of the Anthropic models as the workers who do all the work. And as time passes, I don't know if I'd even do that; the open models are serving SO well.

lelandbatey··on Rob Pike – 'Concurrency Is Not Parallelism' [video] (2012)
No, and that's the point of the article. What you are calling parallel w/r/t IO should be called concurrency (conceptually happening at the same time by virtue of being able to interrupt and resume units of work). The reason IO APIs like you've described is concurrent but not necessqrily parallel is because there is no guarantee in the API that they both happen literally simultaneously; I could build a JS runtime that "works" for all the code written against XMLHTTPRequest (ignoring side-effects) but which under the hood only ever makes one HTTP request at a time. And because I can do that, that means JS code is living in a concurrency-only world, even though as an implementation detail most runtimes support parallel execution of those concurrent operations.
lelandbatey··on HackerRank open sourced its ATS. My resume scored 90/100. Oh wait 74. No – 88
As I understood it, the "randomness" affecting what is selected at any temperature still comes from a PRNG or CSPRNG (or whatever RNG you want, maybe a hardware one), and if you where to swap out that with something deterministic you'd get the same results every time (barring non-determinism in other parts of the OS/drivers/maybe even hardware).

But theoretically, the output of every LLM is seed-driven (or could be if you wrote the software to isolate it) just like any computer software. It's just none of the software written (even llama.cpp AFAIK) chooses to support stable-seeding due to the changes in stuff like CPU/Vulkan/CUDA/Metal differences making it difficult to make consistent.

They could though! Hopefully one day someone implements it into the mainstream LLM-engine software and it gets exposed in the APIs serving the models. It'd do a lot to show folks the "internals" of these models.

lelandbatey··on Age verification is just a precursor to automated attribution of speech
Is there such a thing as "unbiased public opinion" at all though? The memetic effects of language and communication means propaganda and similar tools of rhetoric and leveraged communication will always work, with or without an internet. There's no "solution", only "good enoughs".

Direct democracy is cool, but also impractical. I do not want to vote on every counties appropriations for road maintenance. So what's a level of direct democracy that's "good enough"? How do we make sure we're directly voting in things relevant to our lives? What if "relevant to our lives" is unrelated to our geographic location and is very interests based? If anyone can vote for anything, but most folks don't ever vote for most things, how do you prevent brigading of votes via coordination by groups who see that their group alone can swing what would be a small local vote whatever way they want by virtue of sheer numbers? How do you prevent trolls from going through every vote and just voting no on every "community center paper-and-ink budget" across the entire country?

There are so many questions I have about direct democracy systems! Do you have more information?

lelandbatey··on Show HN: DBOSify – Drop-in Temporal replacement built on Postgres
I asked the DBOS folks about this before; the idea is that there is no "coordination node", only the workers and the DB. See DBOS folks previously: https://news.ycombinator.com/item?id=45186494
lelandbatey··on Codex logging bug may write TBs to local SSDs
Your solution "appears" to solve the problem, but without any information about how exactly that solution works, it's just magic an vibes.

Does the harness parse the contents of CLAUDE.md, see the @AGENTS.md and then inject the contents of AGENTS.md into that file with a note saying "hey Claude-the-llm, here's the contents of AGENTS.md per an @reference"? Does the harness parse and inject but WITHOUT any ceremony telling claude-the-llm that what it's looking at is from another file? Or does the harness do nothing and Claude-the-llm is merely trained to see @references and treat those as "I should go read that file"? Which is it? If it's #1 and #3, then on long contexts/after compaction, then the LLM is still pretty likely to lose the fact that it read that file and re-read it again. If it's #2, the LLM could have the same problem as with the symlinks.

How does it work? The Anropic docs certainly don't say. So what's the best choice? I guess it's magic. For folks like me who care though, I guess there's always Pi or Opencode (or even, writing your own harness [which is shockingly easy if you want it reliable without all the fanciest features]).

lelandbatey··on 'We had to get out of the way': The backlash over delivery robots
Sure, and the delivery robots have people who want the things at the end, and the robots can't (apparently) go in the road.

Roads used to be for people and wagons, till cars showed up and kicked the people off. Now delivery bots are trying to do the same thing, kick the humans on foot off the sidewalks.

lelandbatey··on Local Qwen isn't a worse Opus, it's a different tool
Bashing on ollama is totally warranted, since ollama is a UI skin around llama.cpp and that's it. If all you cared about was "I want to run a model and use it via an API" then the only thing it did was give you a GUI to download models (vs browsing HuggingFace yourself and downloading .gguf files yourself) and a GUI with a button labeled "run" (instead of a run.sh or run.bat script launching llama-server).

That's not _nothing_, but it's pretty close to nothing, and for the prosumer crowd it edges towards "just gets in the way".

lelandbatey··on Local Qwen isn't a worse Opus, it's a different tool
I've tried Opus 4.6 in the Opencode harness through the Github Copilot API, and I've tried Opus 4.8 in Claude Code. I found I preferred Opus 4.6 in Opencode (and in general, I like Opencode much more in that it hid less from me). I found both to be pretty similar as far as efficacy (I was surprised that Opus 4.8 felt like such a minor improvement over 4.6).
lelandbatey··on Ask HN: Has anyone replaced Claude/GPT with a local model for daily coding?
I use it, it's good, I get work done, but know that they really mean it when they say

> "Quality is like running edge models from 8-12 months ago"

Don't expect Opus, expect more like Haiku. If you micromanage it, you'll get great results. If you want it to be a human in a box, it'll flounder.

lelandbatey··on A €0.01 bank transfer could compromise a banking AI agent
You can do this, it is useful, but it's just not the same as where the goalposts are now which is: the AI is a person in a box and can do everything a person can.

If we actually limit them to "only accepts tiny ultra well defined problems and ultra well defined outputs" then theycease being a $10T/year idea and become a merely $10B/year idea.

Thus, it is not exactly popular at the moment.

lelandbatey··on Zeroserve: A zero-config web server you can script with eBPF
I suspect it's worth exploring if that will change as AI is allowing more and more "human words -> machine effect", which may be more ergonomic for the AIs. It could take a long time for that kind of shift to become clearly a good idea since the AI can make either work.
lelandbatey··on WSL 2 is getting faster Windows file system access
Or, as they said, they didn't want to have to think about it so they chose to switch.
lelandbatey··on Gooey: A GPU-accelerated UI framework for Zig
You should read the link they provided which goes into detail on the architectural shortfalls of Gooey due to an accelerated development.
lelandbatey··on The Website Specification
It's done that way as an overreaction to B2B customers which may want totally isolated per-tenant systems.

Take Okta login for example. Okta wants to offer big hyper-secure customers an option of "if you want, we can run our system in your cloud/data-center/whatever". To support that kind of system, you go to to the https://login.okta.com/ page and enter your email, JUST your email. Okta uses that to look up which customer tenant you belong to, then sends you to customer.okta.com where you enter your password. This way, the password only goes through infra owned by big-customer.

Okta then just builds everything with his indirection so they can move customers to it.

lelandbatey··on I think Anthropic and OpenAI have found product-market fit
Something is definitely going wrong with your Qwen setup, in the link you posted it starts and ends with a compaction step due to a 4k token context limit. Qwen 35b supports I think up to 200k+ context limit (though I run only with 128k), that seems to be a major source of the problem.
lelandbatey··on I think Anthropic and OpenAI have found product-market fit
A gaming PC can already host models that perfectly serve casual users who just want recipes, todo tracking, picture identification, etc. E.g. Qwen 3.6 35b which will run on a $650 GPU at 75 t/s (Nvidia 1660 ti 16GB).

Said model will also run as a tool-calling coding model excellently (it's no Opus, but for a thing that once set up is just the cost of energy, it's incredible). It can type faster than you can, probably 10x faster, so with guidance it'll make you faster. And it's free.

It's here. If folks want ChatGPT without a subscription, they can have it today on their computer. The only money to be made is in the high end models doing "serious business" work spanning 1M+ token contexts and massive uncertainty. Everything else is already set to be eaten by today's local models.

lelandbatey··on Search engines alternatives now that Google isn't Google anymore
Perplexity.ai

It's an AI like Google's "AI mode", in that it also surfaces URLs. I have not found it to be a good search engine replacement.

lelandbatey··on Scammers are abusing an internal Microsoft account to send spam links
The domain is Microsoftonline.com

Typically it's a mis-placed feature. Something like "send an email alert when a thing happens" and they let you control what goes in the message body as well as who the message should be sent towards. Sounds reasonable on the surface, but without guardrails it lets folks send arbitrary emails from your domain.

lelandbatey··on Green card seekers must leave U.S. to apply, Trump administration says
So, love and families, none of that counts for shit beneath the boots of bureaucracy? Send the kids away from their mother, she didn't navigate the Kafkaesque trap correctly so now we must ruin their lives. Nothing about that seems... Wrong? Because up until yesterday, the policy of the United States was that such a thing WAS wrong.

> A US citizen is free to marry anyone, regardless of citizenship. There is no automatic guarantee, however, that the couple can both live in the US.

While you, like USCIS, may be correct that technically the de-jure rules state that there is no automatic guarantee that spouses cannot both live together in the US, the de-facto reality up until yesterday, for all of living memory is that YES, spouses are guaranteed to be able to live together.

← PreviousPage 2 of 34Next →