Recent submissions

Comment · 2 months ago
nightmare for anything that relies on checksum based security :D
Comment · 2 months ago
"He's so dense that light bends around him"
Comment · 2 months ago
> strongman/woman warlord

any examples of women warlords ? I'm interested because both gendering and not gendering that sentence would upset feminists and I can't tell if this is trolling or whether more thought went into why gendering felt like the safe bet here.

Comment · 2 months ago
Comment · 3 months ago
also _"materially"_ ...
Comment · 3 months ago
> it’s coming from a press office, not researchers

fwiw, the pre-print reads:

   To define committed collapse, i.e. that past and unavoidable future emissions have already locked in collapse, we assume that global emissions cannot be mitigated from peak to net-zero any faster than 35 years.
...

    The ‘2025 peak ensemble’ therefore quantifies the probability that AMOC collapse is already committed, i.e. past emission have already locked in the collapse by 2025;
Comment · 4 months ago
most of it is overstated because of marketing. in fact the ban looked like an inside job by the current administration to play with the stock value. if the ban did anything it was to make every n00b agree that Anthropic was so far ahead of its times it needed to be banned.
Comment · 4 months ago
good to see this but all of them pay taxes in the US. we need something like this in Europe as well. think global but act local ...
Comment · 4 months ago
> it's a lot of work that no one's being paid to do,

aren't they like some kind of non-profit (in the legal sense) that is still able to take a lot of money (from players like Google and Co, to justify fixing this), as opposed to ... say the Zig foundation, ... that is is also "non-profit" but can't get money the same way?

Comment · 4 months ago
> I was able to identify, diagnose, fix, ...

a link to the PR or Changelog would strengthen this comment that it actually happened?

Comment · 4 months ago
my comment was not an endorsement of codex. when I said "also" I was referring to openai as the other problematic company :)
Comment · 4 months ago
Claude also just updated their privacy policy so they can shove a "please verify your identity" reply in your face after they flag your chat for "malicious activity". This is already common practice with Codex.
Comment · 4 months ago
the problem is that the guardrails prevent us from performing real security work which is friction that is incurred by the legitimate user but not by a moderately sophisticated threat-actor.

for example in my org it is part of the culture that security has no seat at the table. that is a separate problem, but the number of orgs like mine are more numerous than the number of orgs where security isn't a cost-center.

we find lots of stuff because low-hanging fruit is everywhere. hecking heck: I'm a fruit.

and when the cost of fixing is even the slightest inconvenience to devs we will not fix it, but continue sitting on the risk until the cows come home. In such a place a new critical finding isn't even novel. Instead our job moves to to combining different vulns that we already have, and try to show managers how bad it is.

the common retort from management is: proof to me why this is an issue, and why engineering should divert their attention to it. And unless my team can proof why X can be exploited, or Y can be bypassed, or Z can gain persistence, ... the vulnerabilities will remain. I have been in discussions where the business demanded to see an exploit so they can justify the cost of fixing it. low-cyber-maturity doesn't even describe it. we are not a mom and pop shop but have 110K employees worldwide. and again - we are not uniquely insecure.

so these guardrails aren't helping because the moment the chat has any offsec artifacts, or even just a single wrongly worded phrase anywhere in the workspace, the session is flagged, you need to downgrade the model.

what adds insult to injury, is that the guardrail is just a way to funnel users into the Ai company's "cyber marketing" program: "your chat has been flagged, please proof your identity and hand over your passport data so you can sign up to our TrustedCyber program". Bitch please you have my payment information, use that??

if you consider bug-density (security defect density) per LoC, it is even more of a sh1t show: no restrictions apply for developers to push their buggy code, but the security team needs to somehow proof that they aren't the malicious party?

totally off - considering the right way to build defensive/offsec/malicious tooling with AI isn't by using frontier models ... but run a serious of agents on tightly scoped tasks. see https://securitycryptographywhatever.com/2026/03/25/ai-bug-f... and https://aisle.com/blog/ai-cybersecurity-after-mythos-the-jag... - this shuts out the average joe who works in an org where cyber security maturity is poor. joe does not know about how to orchestrate a fleet of agents and give them muppet names. all he knows is that the good guys are losing the fight.

Comment · 5 months ago
DoHoT implemented with dnscrypt-proxy is my personally fav way to solve this ... https://github.com/alecmuffett/dohot

speed (over tor) is not a concern either when much of it is served from the cache. alec muffet has the right ideas. but you might want to study his threat-model before copy pasting.

Live from the official Hacker News API

A modern reader for Hacker News · SvelteKit + Skeleton