Explore >> Select a destination
|
You are here 
|
rishikeshs.com | ||
| | | | |
ezyang.github.io
|
|
| | | | | In cooking, mise en place refers to the practice of organizing and arranging all of the ingredients that will be needed during a shift, so that one does not have to scramble to find the things you need when you are on task. Mise en Place for your LLM is ensuring that all of the rules, MCPs and general development environment for your model may need are properly setup before you have a task. In my experience, Sonnet 3.7 is not very good at fixing a broken environment; vibe coding to fix a mutable, live production environment is like randomly copy pasting commands from StackOverflow and hoping that something good will help. More likely than not, you're going to just irreparably destroy your environment. So make sure that everything is setup correctly, so that Sonnet doesn't go down a big rabbithole trying to debug why your environment isn't working when as an agent it tries to run some tests. | |
| | | | |
www.softdevtube.com
|
|
| | | | | Large Language Models (LLM) have enabled machines to write code. The resulting movement, AI-assisted coding, promises to improve the productivity of software developers. However, AI-assisted coding is still in its infancy. This implies that we should embrace it with caution, guardrails, and realistic expectations. This talk presents both the short- and long-term implications of using | |
| | | | |
nonint.com
|
|
| | | | | ||
| | | | |
www.softdevtube.com
|
|
| | | Computers are orders of magnitude faster than when most of us started programming and yet a lot of software runs much slower than it should. Nobody likes progress bars. Slow code provides for a horrible user experience, drains batteries faster, and increases our cloud bill. This session explores some of the reasons why software is | ||
