on a break from CISO duties, building chatbotkit.com

Joined February 2008
1,169 Photos and videos
Petko D. Petkov retweeted
Introducing crmkit - an open-source, agent-first CRM your AI drives over plain HTTP. Headless, a single Go binary, with a one-click MCP connector for ChatGPT and Claude. chatbotkit.com/changelog/int…
1
1
90
1
84
What follows next is purely speculation and it is based on my own observations and thoughts but based on what I've seen the old RBAC models, while being almost broken before, now it is fully broken, with the fact that now coding assistants and engineers are working on multiple unrelated projects simultaneously - especially working on wild experiments they had no time for previously. The risk of supply chain issues has increased dramatically in the enterprise. Again, I am not saying it is related but I think it has an impact. Now in many places it is encouraged by coders and managers to vibe stuff on their own devices. Soon or later it will become a problem, especially for those that have no idea what they are doing. I am not saying it is related but I feel that it coincides perfectly. I just cannot believe there is no underlaying thread going through all of these recent supply chain issues, and yes there are some hacking groups that specialise in this, sure, but it is because the bounty is plentiful.
82
Build a Market Bot that continuously monitors the AI agents ecosystem. Track trends, spot emerging patterns, and stay ahead of the curve with autonomous AI monitoring. Check out the full example here: chatbotkit.com/examples/ai-m…
50
1
93
Build your agent harness against weak open-weight models. It comes out far more robust, and you find the bugs before your customers do. chatbotkit.com/reflections/b…
62
A researcher spent $1,500 testing if LLMs could hack a vulnerable app. GPT-5.5 nailed it 7/10 times, while Claude kept having ethical crises mid-exploit and Gemini refused to even try. More information here kasra.blog/blog/i-spent-1500…
2
119
We are launching Blueprint Bulletins, a shared message board that lets agents within a blueprint coordinate by leaving short, self-expiring messages. Check out the full changelog: chatbotkit.com/changelog/int…
39
Red teaming used to be expensive and rare. An AI agent that attacks your systems around the clock changes that. Cheap, always on, and available to attackers too. Read the full reflection: chatbotkit.com/reflections/a…
35
pewdiepie chatgpt clone - 100% vibes 0% reliability
1
80
Uber created the exact conditions for this disaster
2
77
OpenClaw on Windows. What could go wrong?
68
AI coding assistants promising instant productivity, then quietly donating all the savings back to debugging, maintenance, and code review.
3
11
954
This is how we build visuals these days - not with Figma but with a dedicated tool we built for this purpose. You can use it now on labs.chatbotkit.com
1
65