Samuel ツ
@samuellhuber.eth
full llm.txt files from web where it's just all of the docs rarely make sense. An agentic approach allowing to navigate the docs and pick what is needed or manually pasting relevant pages is way more efficient
4 replies
0 recast
13 reactions
Dan Romero
@dwr.eth
Doesn’t Karpathy think one big context window is more effective?
2 replies
1 recast
4 reactions
Samuel ツ
@samuellhuber.eth
For large code bases they are not yet big enough Also if I can do the picking of important info for the model with clear instructions the task description gets more precise leading to better outcomes I believe eventually we just put as much as we want in there but not today (though way way better then 6 months ago already) Most of what makes cursor better then anything else is its ability to manage what’s important to include
2 replies
0 recast
0 reaction
Jason
@jachian
Tool dependent too. I started trying Augment because I’d been told its focus was on indexing enterprise scale databases. Cursor/Windsurf type tools still do some awkward truncations And most teams don’t have Meta scale to custom fine tune your model to just understand your stack
1 reply
0 recast
2 reactions
Samuel ツ
@samuellhuber.eth
How’s augment ?
1 reply
0 recast
1 reaction
Jason
@jachian
I like it so far, but none of the repos I’m in are big enough for me to say much about its indexing yet. I like the built in meta prompting, but I can see how a power user racks up a bill on this thing
0 reply
0 recast
1 reaction
