Tootfinder

Opt-in global Mastodon full text search. Join the index!

@stsquad@mastodon.org.uk
2026-10-18 15:59:59

I have been playing with local small agents like #qwen (qwen3.5-9b-artemis) that will fit into my "tiny" 8gb GPU. I left it the task of fixing a rebase conflict which it managed. There where some questionable forward declarations which I removed but it at least had the patience to grind through the build and test. It's also helping my bread dough rise 🔅 🍞😉

@rasos@fairmove.net
2026-10-04 17:29:46

Will the #AI #investment #bubble burst? I say the 1 Trillion market deflates in 2027.
#Qwen 3.8 class models are al…

Capital Expenditures of AI Hyperscapers 2025 peaks 2026 then 2030  flat tire
@veit@mastodon.social
2026-08-28 13:19:45

The AGENTS.md file simply uses up tokens – nothing else. This was the conclusion reached by researchers at ETH Zurich: ‘Surprisingly, we find that providing context files does not generally improve task success rates, while increasing inference cost by over 20% on average.’
#LLM #AgenticCoding #Claude #Codex #Qwen