kami23

Ah I interpreted it as 'of course they can't stop distillation if they couldn't stop a model from escaping its sandbox'

I can see how there's a big leap there, but I agree somewhat. If they are aware these are happening and can detect it as it is happening why are they not stopping them? What do you do there? It'll be cat and mouse for a while. Thinking of reasons they wouldn't try and stop it is just a lot of speculation in my brain.

It's probably a way harder problem than I think it is, but they are aware of them now, so I assume they are going to get more aggressive about it.

Let's say then that they can't detect them near real time or even a bit after, maybe they do have a big observabilty gap that no one has solved adequately.

The speed which they add features I've needed for governance is pretty close to the speed I 'manually' write those for my company. To me personally we are all just going fast and breaking everything and not having enough time to set up safe environments. I'm sure it's in the backlog.

That they should be able to find distillation 'attacks' if they had enough observability.

Kratom has been around for a while, I remember seeing it in headshops at least a decade ago.

I remember watching GigaOm on Revision3 back in the day, I think I stumbled upon it via Diggnation... nope I think it was CrankyGeeks actually.

It was the first newsletter I actually subscribed to back in the day! Sad to hear about his passing, his appearances on podcasts introduced me to the more business side of tech where I was just a hobbyist teen at the time.

RIP

I haven't had time to read the whole article, but I really appreciate the cross section of the world that reads HackerNews and plays STS2. STS1 and STS2 are my favorite games and to see this pop up here brought a big smile on my face. Thanks for sharing.

I have this same attitude. I've been a linux user for 24 some years I don't need to know why Linux broke, just fix x and move on.

I used to spend hours debugging video card issues and other modifications I've liked to make over the years and being able to describe my ideal system admin setup I could get onto what I actually wanted to do.

Heh, thinking about it now, I broke a MBR on a Windows install as a kid and if I would have had these tools I would have been able to fix it immediately, but back then it took me using enough Linux booted off live cds to learn debugging techniques to fix the MBR. And debugging is one of my best skills.

Seeing subagents working in Claude last summer, I saw it and told myself my job is going to be different and I can automate the hell out of my workflow

This read like poetry to me. Thank you for sharing it.

I have a linguistics background and a lot of my philosophizing lately has been on whether or not the emergent abilities of the LLMs is deep down a similar mechanism that creates our consciousness.

For a little bit I was working on having linguistics based evals for a kaggle competition. My challenge was whether or not I could mask things well enough to not trigger its internal state of certain phenomena, and that sent me down a rabbit hole that I'm still exploring.

This story resonated with a lot of questions that can come out of figuring a good solid answer to the what is consciousness question. The one I triggered for me is: Is our perception of time just a slow thread in the giant GPU we are running the universe on? Or more generally, what is time? That's a fun YouTube rabbit hole if you ever need one.

I am unsure what you mean by hard evidence in the context of AI then, what is the evidence we are negating in your view?

For video/image stuff I found the ability for the LLMs to use ffmpeg and imagemagick to be quite fun.

I have it record a series of gifs or videos that I look over. If something looks off I'll dig into it, but I break down work into very very small chunks that are usually easily verifiable or don't require multiple steps.

Another thing I have in the general sdlc process is having it add enough logging to verify features are turned on, configured as we expected, and that becomes enough feedback for most of my features.

I've been mostly focusing on being able to replicate this across stacks greater than 3 projects so far (with the eventual goal of having an agent be able to orchestrate our complete infra stack, and this being a large component of a DR plan to rebuild).

None of this is really new for us, I'm just the most knowledgeable in my group in how the different products across teams glue together so I've been creating these rube goldbergs as a prototype, and then having it iterate on codifying the parts that don't need a constant LLM. We were blessed to have an engineer a decade ago build out tooling for local container automation that matches 95% of the deployed infra stack. That last 5% sucks when you fall into it, but that's always been a truth. I've added and expanded the tool over the years with making it act more like the deployed environment networking wise, but a lot of things don't end up working well in docker containers on M series macs when most of our complicated virtualization in our private cloud can't run on them yet...

This is where most of my productivity gains have come, I have a special harness I move from project to project now that does my testing orchestration, lots of my work day is setting up a prompt or two early and just letting them loop till they return evidence that the feature is working having gone through the big QA loop.

I've slowly been optimizing for token use through the stack and Claude ends up making very tight for loops for most of the process and keeping token count even lower. It's been nice. A lot of my toil at work is just gone.

Hey thanks for the note about the discord!

I have also been finding the MCP auth story to be really lacking was excited to see OAuth 2 support until I tried to get it to work at work and realized our idp implementation didn't support 2.1, and went into the spec and started wondering if anyone had a good experience yet. Luckily most of our environment can settle on a OAuth token env var standard until that's all in order.

Exactly, and for a given task you don't need to recall what your friend's brother's name is to do a git commit and push. There's a pull for more context to make these things better, but also the pull to make these execute in such a small context effectively when appropriate.

I'm more on team small tasks because of my love of unix piping, I keep telling folks, as a old Linux dude, seeing subagents work together for the first time felt like I was learning to pipe sed and awk for the first time. I realized how powerful these could be, and we still seem to be going that direction.

I kept reading about how bad Android Auto was for years but we finally bought a more modern used car and I can't believe they would ship that experience to customers. I had a week where I just had to unpair and re-pair Everytime I got in the car.

I would love to read about why that stuff is the way it is from the engineers, hmm that might be a good spelunking. I really must be missing something that makes it harder than I think it really should be.

Why not explain why you think that? We can't all be perpetually online to have an opinion about a one website that shows up occasionally on this site.

Hah same exact setup one brick two ports and it charges everything even my laptop! I've been eyeing some of the ones with built in batteries, but I get a lot of mileage of one brick in the bag.

The steam deck forced me to finally pay attention to the usb-c ecosystem and I can only imagine how some non tech people might get with mysteriously bad or slow charging.

I find it crazy that Apple went back to magsafe in the m4 (maybe earlier but that's the machine I have at work). But at least you can still charge over usb-c.

When I've been working on stuff that requires a SSO login, I noticed that it makes, what I considered, hostile anti-user choices in defaulting to tracking pieces of information I didn't want to track and hadn't mentioned.

Fair that I didn't instruct it explicitly to make more pro-user choices, it just seemed to think slurping as much information into the backend was an default intention. Wasted a few more tokens to iterate on it to remove things, but it was IMO interesting enough that I finally submitted feedback around what I imagine is an interesting training problem.

This reminds me of the old internet for some reason I can't really nail down, but maybe the club penguin-ess of it.

I would love to work for NASA so much even at a significant pay cut, but almost everything I've read in the past was they still do drug screenings for a lot of positions I was interested in. Maybe someday they will pull their heads out of the dark ages.

Eh there's also introverts like me that find typing too slow and having a conversation with a computer is my ideal interaction :)

In my case I have almost all notifications disabled so maybe there's an option somewhere. Generally find those notification badges too powerful for me to not check and then get waylaid doom scrolling/watching, so I've made it a habit to always disable them everywhere.

Somewhat tempted to re-enable it as I only really comment on videos that are for very very niche communities and I'm usually answering or asking questions.

I went to see if I had any replies to a comment I left on a video for the first time today and it's really hidden to get back to them if you don't remember the exact video. I wonder if it's purposeful friction or just not a priority.

Sounds like we need another standard. /s

This is one of the first tech waves where I feel like I'm on the very very groundfloor for a lot of exploration and it only feels like people have been paying closer attention in the last year. I can't imagine too many 'standard' standards becoming a standard that quickly.

It's new enough that Google seems to be throwing pasta against the wall and seeing what products and protocols stick. Antigravity for example seems too early to me, I think they just came out with another type of orchestrator, but the whole field seems to be exploring at the same time.

Everyone and their uncle is making an orchestrator now! I take a very cautious approach lately where I haven't been loading up my tools like agents, ides, browsers, phones with too much extra stuff because as soon as I switch something or something new comes out that doesn't support something I built a workflow around the tool either becomes inaccessible to me, or now a bigger learning curve than I have the patience for.

I've been a big proponent of trying to get all these things working locally for myself (I need to bite the bullet on some beefy video cards finally), and even just getting tool calls to work with some qwen models to be so counterintuitive.

Hah! I made this at work, when I started getting Claude to record the replication and demonstration of the fix as gifs on PRs people finally started asking me about the cool things I was doing.

The reproduction has been one of the things I've been struggling with in regards to consistency of bringing up the right envs. At the moment I've been approaching it as a MCP server that holds a few tools to bring up specific versions or branches of my stack to then find where a bug was introduced, build that commit prove that it wasnt in the previous one, and then fix it and run the full stack again with the fix component, then run through our local integration tests.

This is the stuff that makes me feel like I'm on steroids now, my whole dev debug process can be run with a few instructions, game changing.

Been working on something that I use daily, and decided I wanted to see what kind of other ideas I could get out of it, it's very basic article to speech using piper models at the moment.

https://reader.n0tls.com/

The part I cared about was being able to send links via one click in my browser or two taps on my phone as I want to read every HN article who's title I find interesting, but don't have the time to read right at that moment.

It then at the moment publishes it to an RSS feed so I subscribe to it in Podcast Addict, but I've also just been using the web app as my reading list and tracker.

Been playing around with different settings on the piper models and different techniques for getting the most out of my four dollar instance:

https://experiments.n0tls.com/

Up next is to work on making the voice better (I'm impressed with the out of the box stuff already), and then making it better at finding the real content on a page and only recording that. It's a problem space I don't know much about, but find fascinating, been fun so far.

I just did this over at Hetzner and Claude admins it for me so I don't need to learn the CLI or anything, describe the proxying I want, and it setups up a bunch of small side project pages for me.

Cool to see others on this thread.

Here's a post I wrote about how we can start to potentially mimic mechanisms

https://n0tls.com/2026-03-14-musings.html

Would love to compare notes, I'm also looking at linguistic phenomena through an LLM lens

https://n0tls.com/2026-03-19-more-musings.html

Hoping to wrap up some of the kaggle eval work and move back to researching more neuropsych.

I am also of this opinion that a lot of this can be solved in time with a harness. And whole heartedly agree that there is a class of webapp that has been trivialized that can make a mom and pop shop up to 'enterprise' (80% of our architecture seems to center around the same pattern at my $DAYJOB) run just fine if they accept some of the vibes.

This type of works seems to be happening as a lot of orchestrator projects that pop up here every once in a while, and I've just been waiting for one with a pipeline 'language' malleable enough to work for me that I can then make generic enough for a big class of solutions. I feel doomed to make my own, but I feel like I should do my due diligence.

I tried using hooks for setting up my DIYed version of what channels is now in Claude. I had Claude writing them and not really looking at the results cause the vibes are strong. It struggled with odd behaviors around them. Nice to see some of the possible reasons, I ended up killing that branch of work so I never figured out exactly what was happening.

Now I'm regretting not going deeper on these. This is the type of interface that I think will be perfect for some things I want to demonstrate to a greater audience.

Now that we have the actual internals I have so many things I want to dig through.