Explore >> Select a destination
|
You are here 
|
sean.heelan.io | ||
| | | | |
www.softdevtube.com
|
|
| | | | | Programming history is filled with bugs that turned out to be features and limitations that pushed developers to make even more interesting products. We'll journey through code that was so 'bad' it was actually good. Along the way we'll look at the important role failure plays in learning. Then we'll tame our inner perfectionists and | |
| | | | |
ezyang.github.io
|
|
| | | | | The tail wagging the dog refers to a situation where small or unimportant things are controlling the larger or more important things. A common reason this occurs in software engineering is when you get too absorbed in solving some low level problem that you forgot the whole reason you were writing the code in the first place. LLMs are particularly susceptible to this problem. The problem is that in the most common chat modality, everything LLM does is put into the context. While the LLM has some capability of understanding what is more or less important, if you put tons of irrelevant things in the context, it will become harder and harder for it to remember what it should be doing. Careful prompting at the beginning can help, as is good context hygiene. Claude Code does something smart where it can ask a subagent to do a task in a dedicated context window without polluting the global context. | |
| | | | |
www.spinellis.gr
|
|
| | | | | ||
| | | | |
finnstats.com
|
|
| | | Top 5 Books on Data Science with Python, One of the most popular programming languages in the field of data science is Python. | ||
