Currently we are targeting June 26th as the day for the online event.
We still like a few more talks, so we’re extending the deadline for proposals until June 5th. We’ll then notify all speakers by June 12th, which will give all speakers 2 weeks to prepare their materials.
Right now most of the talk proposals are experience report-style talks, which is great! We’d be very interested if more folks have tools they use for leveraging LLMs. As a reminder, just email me at jmct@haskell.foundation with a short 1-2 paragraph talk proposal.
My favorite YouTube Haskeller Impure Pics had a great video about it. VERY interesting. I like the idea of guardrails on LLM’s and Grace achieves that quite elegantly. If prompt engineering is normally a declarative process, Grace changes that by using functional programming’s paradigm to encapsulate agents into safe(r) sub-processes that the type system is then able to check and iterate through within that sub agent sandbox. The way we protect our data through encapsulation and type checking is exactly how Grace is able to add those guardrails on these notoriously and confidently incorrect hallucination machines.
