Viewing profile — tekacs

Yeah, with love the words "open source" mean a lot less here (de facto, of course not de jure) when the resulting open source product is entirely contingent on Cloudflare's PaaS. A…

In this case, and I don't mean this critically, I guess it would technically be, "Instructed model to find efficiencies... reducing inference cost by 20% saving company x billion d…

Gotcha, interesting. I would love it to death if there were a way to run some CLI, maybe on the system, that gave you information on the current replication state of the disk!

This is phenomenal, great work! On the HN frontpage is Superlogical (I have no affiliation) right now, and I used the shell provided by the Kedge News demo to `ssh superlogical.job…

Very well said, thank you! The triple clause here is exactly what I mean.

This is completely backwards. Cybersecurity has an attacker-defender asymmetry that heavily, HEAVILY favors defenders. For starters, a defender gets to pick the surface area, an at…

For anyone who – like me – was hoping for a video to see what it looks like: https://youtu.be/h2V8YyfKCVs?t=4421

Although this is interesting, it's worth noting that she's saying that her departure is for health reasons, so it feels like it'd be a hollow place for us – as HN is wont to do – t…

If you read the article, you'll notice that they're explicitly making sure to block the ones that interactively query specific content too.

I mean that they're telling developers that they should use Cloudflare's platform to build agents, the kind of agents that would go across the web and act on behalf of users... but…

> For all new domains onboarding to Cloudflare, the categories of Training and Agent will be blocked by default on the pages that display ads, while Search will remain allowed by d…

Something fun: on our AWS Bedrock console right now, there's a 'NEW' model called 'anthropic.honey'. Wonder if that's the codename just for this one or in general?

Not what I immediately expected: it doesn't give you the cryptographic identity of the target app, but it does read a lot like a high-quality phishing attack where you get to e.g. …

Given how small the counterexample is... this feels like a great example of where a lot of interesting results are going to be found: not because they were super difficult, but bec…

I have these plan files as well, but it depends on the scope and scale of the things you're executing on, I think. However much detail gets put into the plan, it still doesn't help…

That isn't really a way around it for the kinds of things I'm talking about. The whole point is that getting all of the relevant context to even orchestrate it takes up most of the…

Yep, Max. I would definitely struggle to code with Anthropic's plans on Pro.

When I've asked Codex agents about things that were in their context window, they've never – to my experience – been able to actually retrieve something from before compaction when…

I've implemented a similar approach – although I'm surprised not to see mention of cache prefix busting in there!

I know a lot of people like to say that compaction makes this moot, but the level of detail you lose across compaction is wildly too much for most things that I do, unfortunately. …

You can run ’codex debug models' into jq! I forget whether it's documented or not, and it is kind of annoying that that's how you find it, but it does tell you. Maybe useful for th…

https://github.com/tekacs/fast-rm I've overridden my rm with this, which I threw together for fast-deletes of things like Rust target/ directories, and after seeing the GPT horror …

I came here to say that this is presumably ORE/OPE (order-revealing/preserving) encryption, not FHE, but... It is both remarkable and depressing how _little_ information is given, …