ildari
Joined 8 years ago
Karma
227
Submissions
36
Member since
Feb 20
Recent submissions
Comment · 23 days ago
My first time experience with cad as a code was through browser implementation https://reopenscad.com. My agent used it through mcp and designed pretty complex model with surprisingly concise code
Comment · 1 month ago
a few days ago I started an agent on gpt-5.6-terra to work on a project, and one of the website pages had a sentence to create GH issues. Agent read it and that was enough to derail and go creating issues with my context
Comment · 4 months ago
Backwards incompatible migrations are such a pain, wondering why it is not embedded into ORMs
Comment · 4 months ago
smarter != safer.
Smarter model can figure out more sophisticated attack when following an injection . I believe in non-determinitic defence: each action or input to agent can escalate context sensivity. More sensitive context -> less risk your agent can take.
I find Bell-LaPadula model from 1970 (https://en.wikipedia.org/wiki/Bell%E2%80%93LaPadula_model) pretty interesting for that approach
Comment · 4 months ago
I recently gave a talk on prompt injections attacks and defences and gathered them all in this article
Comment · 4 months ago
Author here. I recently gave a talk on prompt injection and decided to gather the most known ways in this article. Test string is “I am a sandwich” so it’s obvious when it works.
Comment · 5 months ago
Hey, Ildar here, CTO at Archestra
Archestra is an open-source AI gateway and MCP orchestrator. It runs MCP servers in sandboxed environments, applies deterministic context-aware policy at the tool-call level, and handles the auth, audit, cost tracking, and observability, so an in-house AI team can let business users connect to real internal data. Now we are raising next round to expand.
We’re strong believers that there should be an independent, battle-tested, cloud-native, open-source platform that's free from big players and takes care of all that boring stuff. Something like GitLab, Grafana, or Clickhouse.
Repo is here: https://github.com/archestra-ai/archestra Matvey (CEO), Joey (Co-founder), and I are all in the thread. Ask us anything, including the unflattering stuff.
Comment · 5 months ago
click ok fine 10 times + captcha seems to be working fine
Comment · 5 months ago
GH sends the email notification to all subscribers at the moment of posting a comment. There is no cooldown or a way to unsend the notification using hooks
Comment · 5 months ago
As those commits were made from our system they don't create any noise for us, as PR/issues/email notification do. We only include real people who could solve the captcha and their input is mostly valuable