From the course: Exploring Deterministic LLM Programming
Unlock this course with a free trial
Join today to access over 25,500 courses taught by industry experts.
Increasing determinism in deep context
From the course: Exploring Deterministic LLM Programming
Increasing determinism in deep context
- [Instructor] Determinism is a huge problem when working with agentic coding tools. And one of the reasons why is the context is often the problem. The coding tool will need the proper context. Some of the latest coding tools do better at this, but what kind of context are they looking at? And this is where the abstract syntax tree becomes very important. With PMAT or the Pragmatic AI Labs MCP Agent Toolkit, this is able to extract the entire AST of multiple languages and even combine those multiple languages into a deep context. And this allows the coding assistants to then in one particular file, see what are the different functions, what are the different things that happen? Also, what is the complexity? Because it's an annotated deep context, it has things like the probability score, also the complexity, also the code coverage. And if you can look at this in one document, it makes it much more easy to ask…
Contents
-
-
-
-
Illusion of control agents3m 31s
-
(Locked)
Increasing determinism in deep context3m 32s
-
(Locked)
Understanding AST agentic coding3m 32s
-
(Locked)
Understanding complexity3m 4s
-
(Locked)
Understanding entropy3m 27s
-
(Locked)
Understanding code churn3m 24s
-
(Locked)
Roadmap sprints and technical debt3m 9s
-
(Locked)
SATD predicts technical debt2m 40s
-
(Locked)
Provability score3m 13s
-
-