Do newer coding models end up training on the AI slop generated by older models?
As old coding models were writing and pushing code to public, does the new coding models train on them because generated code by old coding models were not so good?
tbharath
Re:Do newer coding models end up training on the AI slop generated by ...
on Wednesday July 29, 2026 @11:20PM (#49105793)
Interesting, how does that work?
Re:What happens behind the scenes when we change effort for same LLM m...
on Saturday July 25, 2026 @12:44PM (#49049121)
But I was thinking Chef is the LLM model. So I was wondering if it is the same model, what actually changes the effort? Is that part of the inference?
Re:Ask HN: What happens when we do compress the context in Claude Code?
on Saturday July 25, 2026 @12:42PM (#49049095)
So it does forward pass once again to get the summary from the whole session as input?
Ask HN: What happens when we do compress the context in Claude Code?
What happens when we do compress the context in claude code? How does the reduce the context with out loosing the details?
What happens behind the scenes when we change effort for same LLM models?
What really happens behind the scenes when we select high effort vs medium effort for the same LLM models?
Ask HN: What will happen to dev work if companies start using LLM coding agents?
What do you think existing developers will work on if companies start using coding agents ?
Re:Ask HN: How can we make use of AI agents with existing GitLab CI/CD...
on Friday January 16, 2026 @02:48PM (#46651240)
But I think it is not using LLM agents, correct?
Ask HN: How can we make use of AI agents with existing GitLab CI/CD pipelines?
We currently utilize GitLab CI/CD pipelines to deploy our Kubernetes clusters. I am planning to integrate AI agents to gather cluster-related data and automate the deployment process. I am considering two primary approaches:Replacing GitLab CI/CD with Agentic Workflows: Is this a reliable strategy? With GitLab, we can easily rerun a pipeline from the point of failure after fixing an issue. I am...