The git-annex maintainer details efforts to remove dependencies containing LLM-generated code, expressing concerns about code quality and ethical implications.
# no LLM code in dependencies
Source: [https://joeyh.name/blog/entry/no_LLM_code_in_dependencies/](https://joeyh.name/blog/entry/no_LLM_code_in_dependencies/)
I've spent about 100 hours of work over the past month to make sure git\-annex can build without dependencies that contain LLM generated code\. At least so far\.
[https://git\-annex\.branchable\.com/no\_llm\_code/](https://git-annex.branchable.com/no_llm_code/)
Needing to review a program's whole dependency tree on an ongoing basis is apparently what programming has come to?
I've found some real stinkers\. Large LLM generated changes being reverted in the next release without any explanation\. An incoherent 1489 line commit message with 10,000 lines of changes to a 26,000 LOC code base\. A LLM prompt to copy code from another project that seems to have only avoided being copyright infringement due to luck\.
I now have additional information about the quality of dependencies which will surely influence future decisions\. As far as I can see, that's the only positive benefit of this work\.
I realize that I am probably trying to hold back the tide at this point\. That appears to be why Software Freedom Conservancy[punted](https://sfconservancy.org/llm-gen-ai/llm-backed-generative-ai-recommendations.html), and I doubt that the FSF will do any better\.
As these dominos fall, I am reconsidering my participation in these communities\. But I continue my work and support my users\.
It may seem easy to prompt a LLM with
> Add fourmolu config and restyled neat format a module
And commit the result and call yourself a 10xer\. But please consider the broader impact of your actions\. \(In the above case, that project lost my further collaboration on it\.\)
git-annex announces a policy to exclude LLM-generated code from its project due to copyright uncertainties, and provides a build flag to avoid dependencies that include such code.
NLNet Labs announces a policy restricting the use of LLMs in code and documentation contributions, requiring disclosure of LLM use and prohibiting AI-generated code.
Introduces ModSleuth, an agentic system that recursively reconstructs large-scale dependency graphs for LLM development by analyzing public artifacts, revealing multi-hop license obligations and documentation inconsistencies.
This paper presents the first systematic empirical study of using visual repository representations to enhance LLM-based coding agents, showing that integrating visual graphs as a supplementary modality reduces token consumption by up to 26% while maintaining or improving issue-resolution accuracy.
A developer with 45 years of experience is building a local-first harness for LLMs with multi-agent logic, soon to be open-sourced on GitHub, and asks the community what features would improve their local LLM experience.