Justin Calmus

Security dude

[Justin Calmus @sumlac]

@bcrypt You're the best, thank you so much @bcrypt (btw: always been jealous of your handle lol)

[Justin Calmus @sumlac]

@MrTuxracer Wrote this too fast; this was meant to be bug bounty platforms*! :)

[Justin Calmus @sumlac]

Can’t stand AI posts

“Real life/world example…”
“That’s not… it’s….”

[Justin Calmus @sumlac]

@trq212 I’ve had this issue several times in the last few weeks. Not sure if I can reproduce, but will be able to provide session data next time.

[Justin Calmus @sumlac]

@HackingLZ Let’s goo!! Happy hacking!

[Noah @NoahKingJr]

Coders in 2030 be like:

[Justin Calmus @sumlac]

@zack0x01_ I made an article on how to do this: https://t.co/KU5mNNsg1v

[Justin Calmus @sumlac]

https://t.co/BHdgChkTEn

[Justin Calmus @sumlac]

https://t.co/BHdgChkTEn

[Justin Calmus @sumlac]

I have a theory...

PSA for everyone who got hit with a full week's claude usage from one prompt this past week

Claude Code has an agentic loop structure where token consumption is O(N²), not O(N). If call #1 sends 10K tokens, call #60 sends 500K. This is especially relevant if claude is having outages. https://t.co/bkX4R2Xu4D

When Opus (or equivalent) has an outage, and your prompt hits just at the right time, during that degraded service API calls will fail but still consume your input tokens. Claude will retry re-sending the context the entire time. That's why O(N²) is very relevant here, we're talking about killing your week's usage with one prompt.

We see a lot of different responses because the outage wouldn't necessarily affect everyone equally. If you hit the bug at the wrong time, you are screwed.

@claudeai please create a circuit breaker and alert users when API is failing. Silent failures are killing progress.

[Justin Calmus @sumlac]

PSA for everyone who got hit with a full week's claude usage from one prompt this past week

Claude Code has an agentic loop structure where token consumption is O(N²), not O(N). If call #1 sends 10K tokens, call #60 sends 500K. This is especially relevant if claude is having outages. https://t.co/HfE4ssbbzA

When Opus (or equivalent) has an outage, and your prompt hits just at the right time, during that degraded service API calls will fail but still consume your input tokens. Claude will retry re-sending the context the entire time. That's why O(N²) is very relevant here, we're talking about killing your week's usage with one prompt.

We see a lot of different responses because the outage wouldn't necessarily affect everyone equally. If you hit the bug at the wrong time, you are screwed.

@claudeai please create a circuit breaker and alert users when API is failing. Silent failures are killing progress.

[Justin Calmus @sumlac]

@thedawgyg @brockpierson Dual boot + tux racer

[Justin Calmus @sumlac]

@altryne 100%, hit the weeks limit immediately from a few prompts.

[Justin Calmus @sumlac]

Will open source just be a great reference tool of the past?

[Rami McCarthy @ramimacisabird]

TeamPCP got an infostealer into LiteLLM

1.82.7, 1.82.8litellm
c2 is models[.]litellm.[]cloud

Act fast. https://t.co/FDoTMHz4yQ

[Justin Calmus @sumlac]

@aroussi @AnthropicAI @claudeai I did reach out through the official support channels and got nothing. Just the AI response.

[Justin Calmus @sumlac]

@nervoir @stuxfdev @verialabs @BSidesSF I have the worst answer for you, because it really depends. MoE applies reasoning way beyond my model, but the model that I have has deep extensive security knowledge. If you wrap claude around it, it's pretty incredible.

[Justin Calmus @sumlac]

@Jhaddix Looks like a great time!