ay

Just block the ingress IPv4 packets with IP options using nftables or iptables and move on.

Why does everything has to come with so much drama these days.

I went down a deep but entertaining rabbit hole in the other direction for fun: https://github.com/ayourtch-llm/fakelinux - initially with the idea “just replace the syscalls in the executable with some sort of a trap and handle that”.

It almost worked, unfortunately MacOS reserves x18 for platform purposes and Linux doesn’t.

The result is some sort of pretty mad contraption which works sufficiently often to compile aarch64 Linux VPP and its dependencies on the Mac using Linux gcc :)

I suppose with some polish it might be useful for something..

Oh the irony of using AI to create a piece of writing complaining about AI :-)

With almost 600 books in my kindle collection over a period of about 15 years, I would like to think I was a relatively active customer. When they announced “your kindle books are just a license to read”, which happened about the time they announced the deprecation of the old format, I went and converted the entirety of my library to Calibre with multiple open formats.

That was in December, I have not bought a single book on Amazon since then, and the kindle app is not installed on my new phone. Just in case anyone from the relevant AMZN department is reading this.

Both you and parent could be right.

There is a fun term “jagged frontier”.

Meaning: one model can be much better than the other one in one thing, and much worse than the other in another thing.

Very interesting!

Architecturally - where do you run Postgres ? I assume it would be external to the cluster ? (doing it internally would create a circular dependency ?)

I’ve made something very similar that is almost backend-agnostic: https://github.com/ayourtch-llm/tttt - and it does auto inject the MCP in case of Claude, but it is trivial to adapt to other backends.

Isn’t that what LoRA does ?

Oh, thank you very much enlightening me! All the time I misunderstood! I guess then IIT it is for me :-)

Hinduism is probably right. Every system of sufficient complexity is probably sentient - even if in the ways we at our level can not fathom.

I tried qwen3.5:4b in ollama on my 4 year old Mac M1 with my own coding harness and it exhibited pretty decent tool calling, but it is a bit slow and seemed a little confused with the more complex tasks (also, I have it code rust, that might add complexity). The task was “find the debug that does X and make it conditional based on the whichever variable is controlled by the CLI ‘/debug foo’” - I didn’t do much with it after that.

It may be interesting to try a 6bit quant of qwen3.5-35b-a3b - I had pretty good results with it running it on a single 4090 - for obvious reasons I didn’t try it on the old mac.

I am using 8bit quant of qwen3.5-27b as more or less the main engine for the past ~week and am quite happy with it - but that requires more memory/gpu power.

HTH.

I dont have big ideas. Some of the more interesting ones that I ended up using but can’t share: a streaming radio for my MP3 collection (runs behind the vpn); a lightweight and self contained webrtc conference server for talking with my family; a process-level virtualization based on KVM.

Of the ones I can share:

Browser-based network tester using webrtc unreliable data https://netpoke.com - use magic code “DEMO” to see what’s it about - the source is at https://github.com/ayourtch/netpoke

A port of the SOTA speech generation model from Python to Rust:

https://github.com/ayourtch/fish-audio-experiment

A study on LLM prompting techniques:

https://github.com/ayourtch-llm/kindness

My own coding agent that i use with my locally hosted LLM for experiments:

https://github.com/ayourtch-llm/apchat

Also LLM helped with a lot of code for my packet mangling library: https://github.com/ayourtch/oside - which, among other things, includes a now battle tested SNMPv3 stack.

A true “stochastic parrot” using hash tables: https://github.com/ayourtch/hashmem

These are the ones I remember. Feel free to scout my GitHub for more. Edit: And of course it doesn’t need to be said that out of ideas I try all of them make it to github. Many end up thrown away.

You don’t know whether your C compiler isn’t doing that either.

I am 50, coding since ~12. Started with Apple II, during the uni times wrote my own editor in assembly for BK-0010 (a soviet computer), then 30 years in computer networking with some high performance dataplane stuff more recently;

The last years somehow it felt like there’s nothing new anymore, the same 10 ideas being regurgitated with slight modifications. I tinkered with AI for the past 2 years but it was mostly a “tool for writing boilerplate”. I have tried a few ideas for agents but didn’t see how it could work.

That changed with Opus 4.6 and the subsequent wave of local models - now I try 10 ideas a day and it’s like magic! And if something doesn’t work - jumping into the code and debugging it is huge fun!

Understanding that the era of the almost-free cloud tokens might come to an end, I run my own harness pointing to my own GPUs running Qwen3.5-27B, and the last few days it has been very busy! :)

My harness doesn’t “pressure cook” since it doesn’t make sense to do that with only one GPU (besides many other reasons), it runs everything in a linear fashion, including subagents, and logs everything - reading the logs as they go by is another cool thing - sometimes I pick up interesting things from it !

The distribution of people’s moods related to AI seems indeed bimodal. And I feel lucky somehow ending up in the “enthusiastic” rather than “depressed” part of it. To the folks in the other one: I am sorry. I don’t know why it is this way. If I knew I might have given unsolicited advice.

Just use iSH and use the local terminal on the iPhone from which you can connect to the Mac terminal. Works well over tailscale, too.

Fixing a non-trivial bug is a great way to learn - assuming they don’t give up.

By virtue of being generators subtly broken stuff, LLMs are well positioned to create very nice learning material.

Same thing about growing the project - having to deal with something too big for AI is a very valuable experience.

And, in my experience, some of the purely human made codebases are strictly worse than LLM-made :-)

I try to buy physical books, and make an effort to buy it elsewhere, with AMZN being the reluctant last resort if I truly can’t find it. I don’t have a specific go to place anymore.

Also, I reduced the buying pace - owning physical books takes up space, so the bar for getting something into the library is now much higher than before.

I have bought more than 600 books over a decade or so;

But after they decided the ebooks were actually just license to read, I did exactly the same as you, and now rather than happily buying from them, actively discourage everyone in my social circle from using kindle.

I am not going back, whoever they decide to blame.

Reading this article is especially amusing since this bit just hit the news as well:

https://www.business-standard.com/amp/world-news/amazon-euro...

I think it’s just some person clauding around, nothing to do with anthropic. They also opened a massive PR against VPP with a bunch of stuff.

Kimi is noticeably better at tool calling than gpt-oss-120b.

I made a fun toy agent where the two models are shoulder surfing each other and swap the turns (either voluntarily, during a summarization phase), or forcefully if a tool calling mistake is made, and Kimi ends up running the show much much more often than gpt-oss.

And yes - it is very much fun to build those!

> Claude doesn't run out of patience like a human being does.

It very much does! I had a debugging session with Claude Code today, and it was about to give up with the message along the lines of “I am sorry I was not able to help you find the problem”.

It took some gentle cheering (pretty easy, just saying “you are doing an excellent job, don’t give up!”) and encouragement, and a couple of suggestions from me on how to approach the debug process for it to continue and finally “we” (I am using plural here because some information that Claude “volunteered” was essential to my understanding of the problem) were able to figure out the root cause and the fix.

In my comment I meant Rust, not Zig, apologies I didn’t make it clear enough!

Put Claude code on top of it and now you have prototypes of what you have in mind written pretty much instantly and they are suitable for reshaping into production later if needs to.

Back at some point on HN, I saw https://generalfuzz.net/acrn/ - and it seems to be useful at least temporarily - in my and others' anecdata. FWIW.

Telenet and Proximus do, so if you are in their service area, why not switch ? (Don’t know about Voo, I live in Brussels).

My mobile connectivity comes via Mobile Vikings which are now part of Proximus - also IPv6 there, and I love their excellent service.

Very nice. One little bug report: maybe delay the appearance of the instructions until the data for the background music finishes loading - else only a short part of it gets played, which is taking away from the experience and the message.

SNMPv3 absolutely doesn’t require PKI nor key management, it works fine with shared keys.

You can take a look at an implementation of that, which I had built for entertainment: https://github.com/ayourtch/oside/blob/main/examples/snmpwal...

"Read diligently" - that’s a very optimistic statement. I can not count how many times Claude (LLM I am most familiar with, I had it write probably about 100KLOC in the past few months) explicitly disobeyed what was written in the instructions.

Also, a good few times, if it were a human doing the task, I would have said they both failed to follow the instructions and lied about it and attempted to pretend they didn’t. Luckily their lying abilities today are primitive, so it’s easy to catch.

I had to do a little bit of “cross-eyeing” and then I can see something that does look like 3D. That said, my eyes are a little weird this way - back in childhood I trained to move them separately as well - a great party trick to freak out the people ! :-))