Best match combines word and meaning matches. Phrases, hashtags, accounts and websites guide which posts fit; timely queries also favor recent posts. Match labels describe why a post appears, not its quality or accuracy.
Slides & recording from my @devoxx.com deep dive: "Agent Loops, Decoded: Fundamentals to Agentic Patterns in Spring AI" 🎥 Recording: youtu.be/Q91obeWeWNQ 📊 Slides: speakerdeck.com/tzolov/agent... #SpringAI #Devoxx #AI #Java #Agentic
youtu.be Agent Loops, Decoded: Fundamentals to Agentic Patterns in Spring AI by Christian Tzolov
Why do 20-step AI prompts fail mid-PR? LLMs have no loop counter. Stuart Feldman solved this at Bell Labs in 1976: give your agent a Makefile DAG. dev.to/gde/stuart-f... #AI #Flutter #Coding
dev.to Stuart Feldman Was Right in 1976: Why Your AI Agent Needs a Makefile, Not a 20-Step Prompt
If I have to hear one more person over the age of 8 listening to a goddamn ai voice saying nonsense at max volume, on loop, I will be losing my mind. You are not a child, you are 40. Stop it. Use a text based shitsite like an adult... No wait... get headphones so I don't have to hear it at least
Big shift in automation: we’re moving from rigid DAGs to dynamic agentic loops. New dev tools focus less on fixed triggers and more on giving LLMs real-time context. Automation isn’t just a sequence anymore; it’s a reasoning layer. 🤖🔧 #AI #Automation #DevTools
AI closed the loop on a vision implant, in a study co-led by UCSB cs.ucsb.edu/happenings/announc…
mas.to
This is also what happens with the very rich. "Your life is just a series of your own preferences" indeed. No wonder billionaires (and their wannabe acolytes) fucking *love* LLMs.
great to have Google's chatbot explain #BAAJA to me
Idea Guys would pop up in the game development community I ran. We actually managed to get some of them to try and make stuff, and through that process, develop their taste. But they had to FAIL at their grand vision first. GenAI simply grinfucks them into deeper delusion instead.
AI is thirsty, but there's a way out. The worry: training GPT-3 drank 700,000 litres of water, and AI could use 6.6bn cubic metres a year by 2027. The Green fix: clean power (over half of AI's water is the power station, not the server), smart siting, closed-loop cooling. Tech, joined up.
Phase 10 complete · neural networks 31 · perceptron on XOR: same weights every epoch from epoch 2; \(h_1 - 2h_2\) on two ReLU units gives 0, 1, 1, 0 31 · 2-2-1 net, 100 seeds: 77 solve XOR; 2-4-1: 100 32 · backprop vs finite difference: \(3.7\times10^{-10}\) 32 · \(\eta=30\): 563 at step 3, then a 4-step cycle Next: transformers and vector spaces. Archive: zenodo.org/communities/mt24-le… #MT24Learning #NeuralNetworks #machinelearning
zenodo.org
That’s Ai “accuracy” in a nutshell.
RecursiveZoom - 2 LoRAs - Smooth Noise - Qwen38-27b - Retro-Futuristic City Stable Audio Tools soundtrack Created with Visions of Chaos softology.pro/voc.htm #ai #aiart #machinelearning #visionsofchaos #softology
Artificial Intelligence. If you know...you know.
#AiCommunity #aivideo #CreativeAi just keep it coming☕
🤭🤭🤭😋
. HMMMMMM.... kind of ironic coming from an F.I. Person such as DumOld TRUMPnSTEIN with his FaKKKe Intelligence who is Clearly an ENEMY of the USofAmerica I prefer F.I. = Fake Intelligence to A.I.=Artificial Intelligence SUPER definitely does NOT apply .
#QP Superstition #aiart #oc #SpookyTunesAI @sexyjutsuai.bsky.social @guruscorpion.bsky.social @spicycreations.bsky.social @originalvelvet.bsky.social @aiartliv.bsky.social @stumblegirl.bsky.social @nevyn79.bsky.social @costalai.bsky.social @cyberdreamsnight.bsky.social @ruby-crimson.bsky.social
reposting for the daytime crew. part of this btw looks back at the repository for updates; I’m going to be adding new features over the course of the next several weeks. Use what’s useful to you and toss whatever isn’t.
Search looks through the last 36 hours of public posts for your words, "exact phrases", #hashtags, @handles and websites, and also finds posts about the same thing by meaning. New posts join about every 10 minutes. We only include posts whose authors allow logged-out viewing (Bluesky) or search (Mastodon, indexable accounts), and we re-check Bluesky authors each time we show a page. Likes and follower counts never decide the order. For meaning matches, query text is turned into a fingerprint on Wildroot’s own server (EmbeddingGemma-300M); it is never sent to another service. Wildroot does not save query text to disk. Looking for posts like one you have? Similar posts. How to opt out.