Were you able to enable extended security updates without logging in?

I've held out for literal years, but that was the thing that finally made me log into an online user account (and start figuring out how to finally cut the last bit of Windows out of my life)

Just pirate the updates with Massgrave.

This seems directed at people sharing low-effort AI-generated open source projects.

At $DAYJOB, there's an internal version of this, which I think just uses Claude Code (or similar) under the hood on a checked out copy of the PR.

Then it can run `git diff` to get the diff, like you mentioned, but also query surrounding context, build stuff, run random stuff like `bazel query` to identify dependency chains, etc.

They've put a ton of work into tuning it and it shows, the signal-to-noise ratio is excellent. I can't think of a single time it's left a comment on a PR that wasn't a legitimate issue.

Yeah, it’s exceptionally easy to set this up and we have the same thing. Except the team hasn’t had time to fine tune it, and it shows.

Yeah, also running a scraper with no rate limit against a government website is a pretty risky endeavor.

> 4mbps write and 30mbps read is extremely slow.

It's even slower when you consider the 360 TB capacity -- it'd take nearly three years to write to the whole thing.

I would argue it's more important than ever to make new languages with new ideas as we move towards new programming paradigms. I think the existence of modern LLMs encourages designing a language with all of the following attributes:

- Simple semantics (e.g. easy to understand for developers + LLMs, code is "obviously" correct)

- Very strongly typed, so you can model even very complex domains in a way the compiler can verify

- Really good error messages, to make agent loops more productive

- [Maybe] Easily integrates with existing languages, or at least makes it easy to port from existing languages

We may get to a point where humans don't need to look at the code at all, but we aren't there yet, so making the code easy to vet is important. Plus, there's also a few bajillion lines of legacy code that we need to deal with, wouldn't it be cool if you could port (or at least extend it) it into some standardized, performant, LLM-friendly language for future development?

I think that LLMs will be complemented best with a declarative language, as inserting new conditions/effects in them can be done without modifying much (if any!) of the existing code. Especially if the declarative language is a logic and/or constraint-based language.

We're still in early days with LLMs! I don't think we're anywhere near the global optimum yet.

This is why I use rust for everything practicable now. Llms make the tedious bits go away and I can just enjoy the fun bits.

Might want to disclose that you built it.

Also, I took a quick look and I don't understand how your tool could possibly produce "even smaller images". The article is using multi-stage builds to produce a final Docker image that is quite literally just the target binary in question (based on the scratch image), whereas your tool appears be a whole Linux distribution.

I am one of the maintainers at this point, fair.

This would be a much smaller drop in replacement for the base images used in the post to give full source bootstrapped final binaries.

You can still from scratch for the final layer though of course and that would be unlikely to change size much though, to your point.

Probably not a bad litmus test for current and future generations of LLMs though, I'd be curious to try it out on the latest crop.

Only so long as nobody knows you are using it. Soon as anything becomes a metric people with game it.

I hesitate to lump this into the "every new technology" bucket. There are few things that exist today that, similar to what GP said, would have been literal voodoo black magic a few years ago. LLMs are pretty singular in a lot of ways, and you can do powerful things with them that were quite literally impossible a few short years ago. One is free to discount that, but it seems more useful to understand them and their strengths, and use them where appropriate.

Even tools like Claude Code have only been fully released for six months, and they've already had a pretty dramatic impact on how many developers work.

More people got more value out of iPhone, including financially.

In defense of OpenAI in this particular situation, GPT 5 can be incredibly jargon-y at times, making it much worse of a learning tool than other LLMs. Here's some response snippets from me asking a question about dual-stack networking:

> Get an IPv6 allocation from your RIR and IPv6 transit/peering. Run IPv6 BGP with upstreams and in your core (OSPFv3/IS-IS + iBGP).

> Enable IPv6 on your access/BNG/BRAS/CMTS and aggregation. Support PPPoE or IPoE for IPv6 just like IPv4.

> Security and ops: permit ICMPv6, implement BCP38/uRPF, RA/DHCPv6 Guard on access ports, filter IPv6 bogons, update monitoring/flow logs for IPv6.

Speaking like a networking pro makes sense if you're talking to another pro, but it wasn't offering any explanations with this stuff, just diving deep right away. Other LLMs conveyed the same info in a more digestible way.

Actually it just demonstrates why ipv6 adoption has failed :)

No one is going to do that for fun and there is no easy path for home networks.

Asking it to clarify costs nothing and you end up getting up to speed with the language of the domain; everyone wins.

> Asking it to clarify costs nothing

It costs the most important thing I got

Deepening your knowledge isn't worth two minutes to you?

Different strokes, that's fair, but geez.

As does avoiding jargon at the cost of clarity, or defining every term for people who already know it.

Probably not as much as people who heavily lean on their tribes lingo want to believe, but yes. I think we would prefer an AI that is fantastic as understanding what we know. If it's not, it costs time either way — which is not great, either way.

Why are you even doing this if you don’t want to learn? And if you can’t be bothered to ask questions, are you even serious about learning?

I always wonder how useful such explanations could be. If you don’t know (or can’t guess) what ICMPv6 is (and how much would knowing it stands for “Internet Control Message Protocol version 6” help?), perhaps you asked the wrong question or, yes, you’re dangerously out of your depth and shouldn’t be trying to implement a networking stack without doing some more research.