Veganism Social

diyelectromusicOh thank goodness for that.The auto "show the closing bracket in the wrong place" feature of the Arduino IDE was starting to get to me...<a href="https://mastodon.social/tags/Arduino" class="mention hashtag" rel="nofollow noopener" target="_blank">#Arduino</a> <a href="https://mastodon.social/tags/AutoComplete" class="mention hashtag" rel="nofollow noopener" target="_blank">#AutoComplete</a>

Your Autistic Life FR/EN/ESMy bf reports having gotten orange chicken aquifers.I blame autocomplete for this disaster!:madjoy: <a href="https://mast.yourautisticlife.com/tags/OrangeChicken" class="mention hashtag" rel="nofollow noopener" target="_blank">#OrangeChicken</a> <a href="https://mast.yourautisticlife.com/tags/aquifers" class="mention hashtag" rel="nofollow noopener" target="_blank">#aquifers</a> <a href="https://mast.yourautisticlife.com/tags/autocomplete" class="mention hashtag" rel="nofollow noopener" target="_blank">#autocomplete</a>

Your Autistic Life FR/EN/ES"Mr. Johnson! How ducking nice to bump into you!""Mr. Joyce! I don't believe my ducking eyes! Duck! It's been so long, old chum.""Say, do you still duck your partners?""Yes, I do. I duck them long and hard!""Jolly good! Well, have a ducking good day, you old duck.""Same to you, ducker!"<a href="https://mast.yourautisticlife.com/tags/duck" class="mention hashtag" rel="nofollow noopener" target="_blank">#duck</a> <a href="https://mast.yourautisticlife.com/tags/fuck" class="mention hashtag" rel="nofollow noopener" target="_blank">#fuck</a> <a href="https://mast.yourautisticlife.com/tags/nonsense" class="mention hashtag" rel="nofollow noopener" target="_blank">#nonsense</a> <a href="https://mast.yourautisticlife.com/tags/autocomplete" class="mention hashtag" rel="nofollow noopener" target="_blank">#autocomplete</a>

Your Autistic Life FR/EN/ES"Did you get the stuff I wanted?""Yep, I got everything.""W.... what is this?""This is the steel wolf you wanted.""I did not want a wolf, much less a steel one.""See here?""Yeah... it says steel wolf. Oh, I know. The autocomplete fucked us over. I wanted steel wool.""Lucky it did not say steal wolf."[Both] "Hahahahahhahahaha!"<a href="https://mast.yourautisticlife.com/tags/SteelWool" class="mention hashtag" rel="nofollow noopener" target="_blank">#SteelWool</a> <a href="https://mast.yourautisticlife.com/tags/wolf" class="mention hashtag" rel="nofollow noopener" target="_blank">#wolf</a> <a href="https://mast.yourautisticlife.com/tags/steel" class="mention hashtag" rel="nofollow noopener" target="_blank">#steel</a> <a href="https://mast.yourautisticlife.com/tags/steal" class="mention hashtag" rel="nofollow noopener" target="_blank">#steal</a> <a href="https://mast.yourautisticlife.com/tags/autocomplete" class="mention hashtag" rel="nofollow noopener" target="_blank">#autocomplete</a>

Adam BeerOkay, one more time for the people in the back.The "AI" (🤮) craze of the past few years is all about Large Language Models. This immediately tells us that the only thing these systems "know" is trends/patterns in the ways that people write, to the extent that those patterns are expressed in the text that was used to train the model. Even the common term, "hallucination," gives these things far too much credit: a hallucination is a departure from reality, but an LLM has no concept of reality to depart from!An LLM does exactly one thing: you give it a chunk of text, and it predicts which word will come next after the end of the chunk. That's it. An LLM-powered chatbot will then stick that word onto the end of the chunk and feed the resulting, slightly longer chunk back into the model to predict the next word, and then do it again for the next, etc. Such a chatbot's output is unreliable by design, because there are many linguistically valid continuations to any chunk of text, and the model usually reflects that by having an output that means, "There is a 63% chance that the next word is X, a 14% chance that it's Y, etc." The text produced by these chatbots is often not even correlated with factual correctness, because the models are trained on works of fiction and non-fiction alike.For example, when you ask a chatbot what 2 + 2 is, it will usually say it's 4, but not because the model knows anything about math. It's because when people write about asking that question, the text that they write next is usually a statement that the answer is 4. But if the model's training data includes Orwell's Nineteen Eighty-Four (or certain texts that discuss the book or its ideas), then the chatbot will very rarely say that the answer is 5 instead, because convincing people that that is the answer is a plot point in the book.If you're still having trouble, you can think of it this way: when you ask one of these chatbots a question, it does not give you the answer; it gives you an example of what—linguistically speaking—an answer might look like. Or, to put it even more succinctly: these things are not the Star Trek ship's computer; they are very impressive autocomplete.So LLMs are fundamentally a poor fit for any task that is some form of, "producing factually correct information." But if you really wanted to try to force it and damn the torpedos, then I'd say you basically have two options. I'll tell you what they are in a reply. 🧵<a href="https://dragonscave.space/tags/AI" class="mention hashtag" rel="nofollow noopener" target="_blank">#AI</a> <a href="https://dragonscave.space/tags/AIHype" class="mention hashtag" rel="nofollow noopener" target="_blank">#AIHype</a> <a href="https://dragonscave.space/tags/autoComplete" class="mention hashtag" rel="nofollow noopener" target="_blank">#autoComplete</a> <a href="https://dragonscave.space/tags/chatBots" class="mention hashtag" rel="nofollow noopener" target="_blank">#chatBots</a> <a href="https://dragonscave.space/tags/debunking" class="mention hashtag" rel="nofollow noopener" target="_blank">#debunking</a> <a href="https://dragonscave.space/tags/georgeOrwell" class="mention hashtag" rel="nofollow noopener" target="_blank">#georgeOrwell</a> <a href="https://dragonscave.space/tags/hallucinations" class="mention hashtag" rel="nofollow noopener" target="_blank">#hallucinations</a> <a href="https://dragonscave.space/tags/language" class="mention hashtag" rel="nofollow noopener" target="_blank">#language</a> <a href="https://dragonscave.space/tags/linguistics" class="mention hashtag" rel="nofollow noopener" target="_blank">#linguistics</a> <a href="https://dragonscave.space/tags/LLM" class="mention hashtag" rel="nofollow noopener" target="_blank">#LLM</a> <a href="https://dragonscave.space/tags/machineLearning" class="mention hashtag" rel="nofollow noopener" target="_blank">#machineLearning</a> <a href="https://dragonscave.space/tags/nineteenEightyFour" class="mention hashtag" rel="nofollow noopener" target="_blank">#nineteenEightyFour</a> <a href="https://dragonscave.space/tags/scienceCommunication" class="mention hashtag" rel="nofollow noopener" target="_blank">#scienceCommunication</a> <a href="https://dragonscave.space/tags/starTrek" class="mention hashtag" rel="nofollow noopener" target="_blank">#starTrek</a>

CM ThiedeI'm finding that having <a href="https://social.vivaldi.net/tags/conversations" class="mention hashtag" rel="nofollow noopener" target="_blank">#conversations</a> with people IRL is becoming increasingly more challenging.Like I'm expected to fill in the finer points with <a href="https://social.vivaldi.net/tags/autocomplete" class="mention hashtag" rel="nofollow noopener" target="_blank">#autocomplete</a> or something.<a href="https://youtu.be/wTDUuBWGtpU" rel="nofollow noopener" translate="no" target="_blank">https://youtu.be/wTDUuBWGtpU</a><a href="https://social.vivaldi.net/tags/MarsAttacks" class="mention hashtag" rel="nofollow noopener" target="_blank">#MarsAttacks</a>

🧿🪬🍄🌈🎮💻🚲🥓🎃💀🏴🛻🇺🇸This thing that <a href="https://mastodon.social/tags/phanpy" class="mention hashtag" rel="nofollow noopener" target="_blank">#phanpy</a> does when you add a <a href="https://mastodon.social/tags/hashtag" class="mention hashtag" rel="nofollow noopener" target="_blank">#hashtag</a> where it shows you how frequently each tag in the <a href="https://mastodon.social/tags/autocomplete" class="mention hashtag" rel="nofollow noopener" target="_blank">#autocomplete</a> has been used needs to be stolen by every <a href="https://mastodon.social/tags/mastodon" class="mention hashtag" rel="nofollow noopener" target="_blank">#mastodon</a> client<a href="https://mastodon.social/tags/fediverse" class="mention hashtag" rel="nofollow noopener" target="_blank">#fediverse</a> <a href="https://mastodon.social/tags/hashtags" class="mention hashtag" rel="nofollow noopener" target="_blank">#hashtags</a>

Pasquale 📷 🇫🇷 🦻des experts <a href="https://piaille.fr/tags/javascript" class="mention hashtag" rel="nofollow noopener" target="_blank">#javascript</a> dans la place ?J'utilise <a href="https://piaille.fr/tags/jQuery" class="mention hashtag" rel="nofollow noopener" target="_blank">#jQuery</a> <a href="https://piaille.fr/tags/Autocomplete" class="mention hashtag" rel="nofollow noopener" target="_blank">#Autocomplete</a> pour récupérer des données dans une base de données. Ça fonctionne super bien, mais... je voudrais que sur un input, la liste déroulante de l'autocomplete s'affiche automatiquement, et je ne trouve pas malgré mes recherches.J'ai trouvé cette solution :$( function() { $("<a href="https://piaille.fr/tags/my_input" class="mention hashtag" rel="nofollow noopener" target="_blank">#my_input</a>").autocomplete({ source: autocompleteValues, minLength: 0 }).focus(function(){ $(this).autocomplete("search", ""); }); });mais ça ne fonctionne pas, sur Brave au tout cas. quand je fais le focus sur my_input, la liste de valeurs ne s'affichent et je dois taper une touche. Une idée ?

Recent searches

Search options

Administered by:

Server stats:

#autocomplete