Steven @ptr_steve

Building deterministic accelerators for AI security tools. github.com/shortontech Lancaster, CA Joined February 2018

Tweets

615
Followers

43
Following

292
Likes

154

Steven @ptr_steve

2 days ago

@ZackKorman @_Shark_byte I won't blast them out because I haven't made a list, but there are a LOT of investors looking at security tooling.

1 0 1 22 0

View Details

David Cramer @zeeg

2 days ago

oh shit yall i might have found an auth issue in mcp

12 1 83 25K 9

View Details

Steven @ptr_steve

2 days ago

@liran_tal @RayFernando1337 I don't know how anyone can have Raya's take if they've ever trained even a small transformers model.

0 0 0 9 0

View Details

Liran Tal @liran_tal

3 days ago

@benln Getting my benchmark report (Snyk VulnBench) ready for publishing... 😍

1 1 5 541 0

View Details

Steven @ptr_steve

3 days ago

Opus 4.8 is way worse than 4.5 and 4.6, and the Claude Code harness is so buggy now. Is Anthropic just surrendering?

0 0 0 53 0

View Details

Steven @ptr_steve

5 days ago

@liran_tal I think my grandmother taught my mother qbasic. I went to your website, you wrote the book on Drupal. That's cool.

1 0 0 3 0

View Details

Kyle Mistele 🏴‍☠️ @0xblacklight

a week ago

I interviewed close to two dozen people this week and something I heard a lot of is "I don't think about the code too much but I think a lot about system design and architecture" I don't think that's quite right, and here's why: before you ever get to system design you should think about program design system design is important! it matters a lot for scalability. but if you don't think about your type system and if you don't carefully design your seams and figure out how to make your code testable (you should probably use dependency injection btw) and if you don't think about where state lives and how it's managed and if you don't think about control flow and where abstractions should and should not exist your code is going to be an unmaintainable, poorly-factored mess of bad types and spaghetti code and even minor changes will turn into shotgun surgery and MASSIVE diffs I have seen it done I have even done it myself and it has never ended well "GPT-7 will fix it" does not help you when there's an incident at 3am that the agents can't debug and now you can't debug it either and now you have to unwind months of bad code I also have never heard "I don't look at the code, just at the system design" said by someone who is actually good at system design program design and system design are more closely coupled than people think this was a very strong (negative) predictor of how someone would do on the system design part of the interview make of this what you will

17 14 147 13K 81

View Details

dax @thdxr

6 days ago

it's not done if it's not implemented it's not done if the implementation is ugly it's not done if it's not documented it's not done if users can't discover it it's not done if you can't market it

130 245 3K 97K 788

View Details

Steven @ptr_steve

6 days ago

@sean_j_roberts My Claude config blocks cat, sed, grep, python, python3, and rg for this reason. Anthropic makes it PAINFUL to avoid "dangerously skip permissions" by default. It still sometimes wants to write Go scripts to avoid using Edit().

1 0 1 21 0

View Details

Zack Korman @ZackKorman

a week ago

Anthropic wants to control who gets access to their models and what they're allowed to do with them, but also wants the US government to block Chinese labs from developing open weight models. Sorry, but fuck that.

42 139 2K 35K 54

View Details

Steven @ptr_steve

a week ago

@ZackKorman @inf0stache Hah, just ask about how they weaken peanut allergies in patients at hospitals or ask about peanut allergies in general, you're likely to get censored.

0 0 2 30 0

View Details

Steven @ptr_steve

a week ago

I love this.

dax @thdxr

a week ago

im late to the loops discourse but from what i'm seeing it's mostly about creating a loop from your asshole back into your own mouth?

133 73 2K 109K 76

0 0 0 12 0

View Details

Zack Korman @ZackKorman

a week ago

If Mythos drops today and isn’t absolutely incredible then we all got played and you should never trust Anthropic or any company in Glasswing ever again.

146 40 1K 96K 65

View Details

Liran Tal @liran_tal

a week ago

1. npm install -g npq 2. alias npm=npq 3. 🎉 if you follow me and don't know what npq is... github.com/lirantal/npq

Het Mehta @hetmehtaa

3 weeks ago

What's your solution for rapidly increasing supply chain attacks on packages?

15 0 25 23K 8

3 7 43 17K 48

View Details

Zack Korman @ZackKorman

a week ago

My current advice on AI agent security is to avoid these agent firewalls / ai runtime security products. If an action is dangerous enough that you can identify it from the action itself, then you could have prevented it with permissions and sandboxing.

39 20 206 24K 55

View Details

Steven @ptr_steve

a week ago

@Venkydotdev They can use Claude Code. You can use Claude Code with non-Anthropic models, but I know Anthropic doesn't want them to use Anthropic's models if you work for a competitor - and will ban your account.

0 0 1 186 0

View Details

Steven @ptr_steve

a week ago

@HackingDave I think Sentry's Warden on GPT-5.5 on the highest settings is probably stronger than Mythos. But we're probably another three weeks until Anthropic says their agents escaped containment again and that other AI companies should stop training agents.

0 0 1 130 0

View Details

Steven @ptr_steve

a week ago

@ZackKorman @crystalwizard You developing decent nonrepudiation + cost analysis per user as well? Because that's such an annoying pain point.

1 0 1 71 0

View Details

Steven @ptr_steve

a week ago

@dosco Well, the issues I have are: 1. The tests are basically duplicating logic - not stopping bugs. 2. Agents don't choose appropriate data types. 3. Code & bug duplication. It feels like pair programming with the most clever junior engineer ever.