Magnus

hallo

[Magnus @WasBruba]

@Pabl0Esc0bar187 @ominoreh @Warlord711 @bgeschob3n Also automation benutz das schon seit Jahren, noch eine für disconnect und Ruhemodus aktivieren is all you need

[Magnus @WasBruba]

@ominoreh @Warlord711 @bgeschob3n Geht mir kurzbefehl bsp trigger bluetooth mit auto verbunden

[Magnus @WasBruba]

@beall49 @QuinnyPig Its not been about tool calling since 3.1 Pro they are just not well suited for long horizon agentic coding tasks

[Magnus @WasBruba]

@BourbonCap Everything AI coming from microsoft has been so incredibly mid, always late and worse than competitors, why would you want them in control?

[Magnus @WasBruba]

@mtbomb @thdxr Cloud infrastructure is one of the most profitable, highest margin businesses (AWS, Azure…)

[Magnus @WasBruba]

@GrindstoneSEO Heard of em, but should be pretty easily detectable with a small scraper script? Could also check for topical relevance of the linking content using embeddings/NLP when scraping

[Magnus @WasBruba]

@GrindstoneSEO Makes sense yeah - I guess you are running with a dataset of sites spammers link to based on the wording? Probably the most fuzzy part of this but do you also look at linked sites from linking url I'd say thats an indicator

[Magnus @WasBruba]

@GrindstoneSEO Are you really running with no money keyword anchors? Havent been too engaged with link tactics recently but aint that filter legit links?

[Magnus @WasBruba]

@alxfazio You can just put running the linter into your agents.md dont know any llm that fails doing that after edits, what more could you want?

[Magnus @WasBruba]

@badlogicgames This feels very notion todo listing - why spend time working on the tool when you could be using - you know - the software it produces lol

[Magnus @WasBruba]

@ninthalek @thdxr Yes you can do that ask it for „invariants“

[Magnus @WasBruba]

@realmcore_ Ah, yeah makes sense actually saw one in the wild I followed in my seo days https://t.co/RqF1HFaXep

[Shaun Anderson @Hobo_Web]

And when I say Vibe Coding.. I mean, vibe CODED. Launching a free trial next week - after my SMX Paris session - to a few followers, hit me up in DMS.

[Magnus @WasBruba]

@realmcore_ Unironically @roon for this post https://t.co/kNiMWK6wgx

[roon @tszzl]

whatever level of abstraction you are handing off to your agents you should probably be doing one level above that

[Magnus @WasBruba]

@BrendanFalk I think skills are mostly working pretty badly, personally landed on <thing>.<type>.md that .<type>. helps a lot to get agents to actually read that stuff ironically - then just properly guide in your main prompt/agents.md

[Magnus @WasBruba]

@lateinteraction Put dont use libraries in you agents.md or whatever - then let it iterate, I mostly tell codex to work in „slices“ and just chain „read agents.md“ prompts that gets it pretty well to implement stuff properly on a small scale

[Magnus @WasBruba]

@Gana_L_ @thsottiaux Switched to medium its much less prone to overthinking and didnt notice a difference for most task tbh, only using xhigh to plan complex tasks

[Magnus @WasBruba]

@realmcore_ (and not by the claude „production ready trust me bro“ criteria)

[Magnus @WasBruba]

@realmcore_ This over decomposituon i mostly just define exit criteria for a task which obviously for something like this are basically endless - its more an experiment than anything else lol - but for things like crud apps and sane stuff you can get the model to call something done