22 builds today for RBs. More than half of them failed – most due to Github's LLM agents having party-time, blocking resources, having clones & downloads fail.Especially lucky are devs of Flutter apps, because in 75% of the cases it's the Flutter clone that fails…What did their CEO say? "We use LLMs, and you'll be left behind"? At least that's what we see. A Git forge where Git operations are failing because of LLM agent activity. What was a Git forge for? 🤔#GitHub #LLM #Reliability
Related
Calling =TECHTO_MLREGRESSION for Machine Learning supervised regression in Excel is just a matter of copying and pasting...
Calling =TECHTO_MLREGRESSION for Machine Learning supervised regression in Excel is just a matter of copying and pastinghttps://thierrymoudiki.github.io/blog/2025/07/06/r/python/te...
An interesting use case for local LLMs that I've been experimenting with: OSINT and research on local policy issues, esp...
An interesting use case for local LLMs that I've been experimenting with: OSINT and research on local policy issues, especially commercially backed developments. A lot of these com...
The cheap agent model has a reliability problemMeta’s Muse Ember is built for tool calls, routing, extraction and coding...
The cheap agent model has a reliability problemMeta’s Muse Ember is built for tool calls, routing, extraction and coding subtasks. Its value depends on how often it finishes routin...