Reposted by Marcel Weiß
Don't trust the transphobes at 404.
Advertisers or "anyone" can't "target those specific people" the way he insinuates.
An ad target group at OpenAI needs to be at a minimum 25,000 matching users large.
This is standard practice in the online ad world (at Meta, Google).
There is *no* […]
mastodon.social
Original post on mastodon.social
![Context files are redundant documentation
We show in Section 4.2 that context files do not provide an effective repository overview. Our hypothesis is that LLM-generated context files are mostly redundant with existing documentation, while developer-provided context files add additional information. We confirm this hypothesis by manually removing all documentation (files ending with .md, example code, and the contents of the docs/) after generating the context file and before evaluating the coding agents, excluding Claude Code for cost reasons, and show the results in Figure 12. In this setting, where context files are the only source of documentation available, we find that LLM-generated context files not only consistently improve performance by
2.7
% on average, but also outperform developer-written ones across settings. This may also explain anecdotal evidence reporting that coding agents perform better after adding context files [31], since many less popular repositories contain little to no documentation.](https://cdn.bsky.app/img/feed_thumbnail/plain/did:plc:gt6dlw5bcrmqva7dvtu3wp47/bafkreidsrm4ufhglmzfcxoxgowf4tmzihmjn5xoz53mxypgrjrp2t6ztya)
