Accelerating Software Development: The LLM (R)evolution
summary
Argues that existing tools get profiler++ behavior with Scalene calling an LLM to suggest optimizations that sometimes yield up to 90x speedups; presents ChatDBG as a debugger agent that uses an enriched stack and language servers to raise automatic bug-fix success from under 25% to over 60% (and ~75–80% with dialogue); shows CY wrapping compilers to explain and patch C++ errors; CoverUp generates validated tests to raise coverage beyond prior state of the art; Flowco turns notebooks into verifiable dataflow pipelines.
AI-written summary · about
chapters (6)
- 0:00The LLM revolution
- 5:00Scalene profiler
- 10:14ChatDBG debugger
- 20:11CWhy compiler
- 26:12CoverUp test generator
- 34:57Flowco notebooks
related talks
44mJoint Keynote Address: Accelerating Software Development: The LLM (R)evolution
01mSpeed Up Your Code With LLM's!
11mDemo: TraceLLM - Harness the Full Potential of your RISC-V Systems with an AI Based, Real-time, RISC-V Embedded Application Debug and Trace Analysis Engine
10mSpeed Up Your Code With LLM's!
01h 15m10x Development: LLMs For the working Programmer
30mEfficient programming with Scala and LLMs
43mFrom Entertaining to Useful: LLMs for Test Tooling
28mGetting More Out of LLMs for Ruby Developers Justin Wienckowski, Jake Gribschaw We're all hearing about LLM tools that are changing on a daily, if not hourly, basis