Viewing profile — ryancoleman

GOAT (Generative Offensive Agent Tester, arXiv:2410.01606): an attacker LLM holds an in-context toolbox of 7 jailbreak techniques and reasons in an Observation/Thought/Strategy/Rep…

Achille and Soatto (Amazon/AWS) model AI reasoning agents as compute-capable stochastic dynamical systems and ask: can chain-of-thought reasoning solve any computable task? They sh…

That's basically how it works! (with human authored functions that validate the result, automatically providing feedback to the LLM if needed)

The initial version on GitHub does not implement caching or memorization but it's possible and where the project will likely head. (FYI I'm on the Strands Agents team).

They're handy for situations where it would be impractical to anticipate the way your input might vary. Like say you want to accept invoices or receipts in a variety of file format…

https://www.lambci.org ?

I'm excited to see what sorts of CloudFormation templates people have lying around or which previously shared templates people find interesting. To continue the show and tell part …

I continue to be surprised by the so-called "S3 Bucket Negligence Award" which feels like the intersection of IAM and S3 configuration ugliness that result in so many public horror…

For example, this Ghost + Gatsby tutorial. https://www.stackery.io/registry/?repo=https://github.com/st...

Developer experience for serverless is such a pain point, spot on. AWS SAM has tackled some of the IaC modeling problem (on top of CloudFormation which is a mature choice) and they…

I really like Ghost https://ghost.org/ It's more for prose than ecommerce but it's really pleasant to use and great for headless through its GraphQL interface. I recently wrote a t…