MattSayar

Yeah, in the cybersecurity space it's a lot more prevalent. TLP:CLEAR, if you will.

In practice, "organization" usually means your company or business. "The community" usually means an Information Sharing and Analysis Center (ISAC) aka a group of similar orgs that share information with each other; think financial services companies in the US, or energy companies in Japan.

Good luck following the Enterprise Edition https://github.com/EnterpriseQualityCoding/FizzBuzzEnterpris...

Like many changes, you originally hate it, then you get used to it, then you hate when it changes again.

I cannot right-click and create a new file.

The "Recents" doesn't contain files I've recently interacted with, and I'm still not sure what qualifies a file to be listed in Recents.

The power from a digital watch is billions of times more powerful than the signal we get from Voyager 1. It blows my mind that we're still able to sense it.

https://public.nrao.edu/ask/how-strong-is-the-signal-from-th...

It's nice to see people putting effort into tackling things from the human side outside of phishing awareness campaigns and annual training. Even CrowdStrike noted in their annual report that something like 70% of successful attacks were interactive intrusions without malware.

I'm on my phone and can't dive deep right now, but are you able to create detections in SIEMs to identify these kinds of users and behaviors based on this research?

Same. When I try to get it to do a simple loop (eg take screenshot, click next, repeat) it'll work for about five iterations (out of a hundred or so desired) then say, "All done, boss!"

I'm hoping Anthropic's browser extension is able to do some of the same "tricks" that Claude Code uses to gloss over these kinds of limitations.

I think I struggle to see much difference between 80s and synthwave? It wasn't until you pointed it out that I noticed any real differences. It might be like musical genres where the deeper you explore a genre, the more you can bifurcate the genre.

Presenting is hard

What's your experience with the quality of LLMs running on your phone?

> FORTRAN was proposed by Backus and friends, and again was opposed by almost all programmers. First, it was said it could not be done. Second, if it could be done, it would be too wasteful of machine time and capacity. Third, even if it did work, no respectable programmer would use it -- it was only for sissies!

- Richard Hamming, The Art of Doing Science and Engineering

What speaks to me about this is how it was presented before LLMs, yet many concepts still apply. For example

> Learn tools, and use tools, but don't accept tools. Always distrust them; always be alert for alternative ways of thinking.

In his closing remarks he says, "The most dangerous thought you can have as a creative person is to think you know what you're doing," because you stop being open and receptive to new ways of thinking and doing things, much like programmers shunned FORTRAN because they were comfortable programming in binary.

Tangentially, I haven't received a Pig Butchering opening text ("hey") in quite a while. A quick scan through my Spam & Blocked doesn't show much either, just a lot of political spam. Did something happen to improve the situation, or am I just lucky?

It's one more step on the path to A Young Lady's Illustrated Primer. Still a long way to go, but it's a burden off my shoulders to be able to ask stupid questions without judgment or assumptions.

What's the superior phase of content organization now?

I know at least a couple LLM providers will do some caching for you automatically now, which muddies the waters a bit. [0]

[0] https://developers.googleblog.com/en/gemini-2-5-models-now-s...

A friend of mine created some business plans to help organizations migrate from cloud infrastructures back to on-prem solutions. Like AI features, the sweet spot is somewhere in the middle: hybrid has its place instead of cloud-only, and AI features have their place instead of "everywhere."

Steve Yegge just did the same thing [0]:

> I did give [an LLM agent] access to my Google Cloud production instances and systems. And it promptly wiped a production database password and locked my network.

He got it all fixed, but the takeaway is you can't YOLO everything:

> In this case, I should have asked it to write out a detailed plan for how it was going to solve the problem, then reviewed the plan and discussed it with the AI before giving it the keys.

That's true of any kind of production deployment.

[0] https://x.com/Steve_Yegge/status/1946360175339974807

My experience with uBlock Origin Lite seems basically the same. I also use NextDNS so that probably does a lot of heavy lifting too

I just wrote a post on my site where the LLM had trouble with 1) clicking a button, 2) taking a screenshot, 3) repeat. The non-deterministic nature of LLMs is both a feature and a bug. That said, read/correct can sometimes be a preferable workflow to create/debug, especially if you don't know where to start with creating.

I tried to make an artifact that would simplify Wikipedia articles [0] but the artifacts stubbornly won't let you do ANY input into them, not even via query strings. I think I'd be able to make cooler artifacts once they allow more input/output stuff. I understand the security issues, and it makes sense to roll this out slowly, but I want it now!

[0] ended up making it a browser extension instead https://mattsayar.com/simple-wikiclaudia/

Our UX designers have been prototyping things they started in Figma with Windsurf. They seem pretty happy with it. Of course there's a big step in getting it production-ready but it really smooths the conversation with engineering.

It took me a few weeks to get access. In the meantime Simon has a decent demo here https://simonwillison.net/2025/May/21/gemini-diffusion/

Optimistically, this will allow smaller teams to do more, hopefully incentivizing the consulting places to help out with harder problems.

Could you have a higher-order reasoning LLM generate a better confidence rating? That's how eval frameworks generally work today

I used Anthropic's new Claude API integration with artifacts to make a probably-worse version that you can play with (after logging in of course).

https://claude.ai/public/artifacts/eb7d8256-6d21-4c85-af9b-c...

I used this GitHub repo as context and Claude Opus 4 to create this artifact

Hey Cliff, just curious: how were you made aware that this post on HN is trending?

The best part is right after the money line: 'Please check ' + issues_url + ' for help.' where issues_url is a github.com link. How are you going to check GitHub if you can't connect to WiFi in the first place?

I like the acronym MELT for Metrics, Errors, Logs, and Traces.