01a04837-bbc2-7aac-898e-afae8dbb2823 post 01a04837-bbc2-7aac-898e-afae8dbb2823 0 Johannes Tigges https://vutuv.de/johannes_tigges/posts/01a04837-bbc2-7aac-898e-afae8dbb2823 2026-08-28 Interessantes Paper zum Einfluss von AGENTS.md et al. Dateien. \ https://arxiv.org/pdf/2602.11988 > Wichtiger Quote aber auch:\ > Limitations and Future Work > Programming languages The current evaluation is focused on Python. Since this is a language > that is widely represented in the training data, detailed knowledge about tooling, dependencies, and > other repository specifics might be present in the models' parametric knowledge, nullifying the effect > of context files. Future work may investigate the effect of context files on more niche programming > languages and toolchains that are less represented in the training data [8, 27]. > > Context files beyond task resolution > In this work, we evaluate the impact of context files on task > resolution rate. **However, other aspects of coding agent performance, such as code efficiency \[14] > and security \[10], would be interesting directions for future work. Security, specifically, was found > to be sensitive to prompt changes in prior work \[37].** Hervorhebung eigene. Im Prinzip also: Spitz, nützlich und was das Modell halt nicht selbst kann reinschreiben, nicht was Captain Obvious auch schon gewusst hätte. Whowouldathought. Klingt wie bei Menschen...😆 johannes_tigges Interessantes Paper zum Einfluss von AGENTS.md et al. Dateien. \ Johannes Tigges johannes_tigges https://vutuv.de/johannes_tigges https://vutuv.de/johannes_tigges/posts/01a04837-bbc2-7aac-898e-afae8dbb2823 https://vutuv.de/johannes_tigges/posts/01a04837-bbc2-7aac-898e-afae8dbb2823.json https://vutuv.de/johannes_tigges/posts/01a04837-bbc2-7aac-898e-afae8dbb2823.txt https://vutuv.de/johannes_tigges/posts/01a04837-bbc2-7aac-898e-afae8dbb2823.md https://vutuv.de/johannes_tigges/posts/01a04837-bbc2-7aac-898e-afae8dbb2823.xml LLM Aiassistedcoding AI research contextengineering 0 2026-08-28T13:48:15Z 3 2026-08-28 2 0 Interessantes Paper zum Einfluss von AGENTS.md et al. Dateien. \ https://arxiv.org/pdf/2602.11988 > Wichtiger Quote aber auch:\ > Limitations and Future Work > Programming languages The current evaluation is focused on Python. Since this is a language > that is widely represented in the training data, detailed knowledge about tooling, dependencies, and > other repository specifics might be present in the models' parametric knowledge, nullifying the effect > of context files. Future work may investigate the effect of context files on more niche programming > languages and toolchains that are less represented in the training data [8, 27]. > > Context files beyond task resolution > In this work, we evaluate the impact of context files on task > resolution rate. **However, other aspects of coding agent performance, such as code efficiency \[14] > and security \[10], would be interesting directions for future work. Security, specifically, was found > to be sensitive to prompt changes in prior work \[37].** Hervorhebung eigene. Im Prinzip also: Spitz, nützlich und was das Modell halt nicht selbst kann reinschreiben, nicht was Captain Obvious auch schon gewusst hätte. Whowouldathought. Klingt wie bei Menschen...😆 2 0 0 @academia@newsmast.community announce https://newsmast.community/users/academia 2026-08-28T11:53:41 newsmast.community @ai@channel.org announce https://channel.org/users/ai 2026-08-28T11:53:38 channel.org false 0 2