mastodontech.de ist einer von vielen unabhängigen Mastodon-Servern, mit dem du dich im Fediverse beteiligen kannst.
Offen für alle (über 16) und bereitgestellt von Markus'Blog

Serverstatistik:

1,4 Tsd.
aktive Profile

#PromptEngineering

5 Beiträge5 Beteiligte1 Beitrag heute
Wulfy<p><span class="h-card" translate="no"><a href="https://blahaj.zone/@piku" class="u-url mention" rel="nofollow noopener" target="_blank">@<span>piku</span></a></span> <span class="h-card" translate="no"><a href="https://mathstodon.xyz/@johncarlosbaez" class="u-url mention" rel="nofollow noopener" target="_blank">@<span>johncarlosbaez</span></a></span> </p><p>That depens what you need the map for...<br>Just because you open a can of beans, doesnt mean you cant pour the contents into a bowl and sprinke them with oregano and grated cheese.</p><p>...or you can add to the prompt "... name the states after their signature dish after a fictional civil war, split into three factions" (as you can see, the 1st cut results need a couple of corrective prompts...but you can surely see the fun.</p><p><a href="https://infosec.exchange/tags/imagination" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>imagination</span></a> <a href="https://infosec.exchange/tags/ai" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ai</span></a> <a href="https://infosec.exchange/tags/maps" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>maps</span></a> <a href="https://infosec.exchange/tags/genai" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>genai</span></a> <a href="https://infosec.exchange/tags/promptengineering" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>promptengineering</span></a> <a href="https://infosec.exchange/tags/fun" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>fun</span></a></p>
Angelos<p>How to Ask ChatGPT Better Questions?</p><p>✨ Do you keep getting “shallow” answers from ChatGPT?</p><p>The secret is clear, detailed questions.</p><p>🧠 The quality of ChatGPT’s answer depends on the clarity of your question.</p><p>Bad prompt: “Tell me about healthy food.”<br>Good prompt: “Create a 5-day Mediterranean diet plan with 1,800 calories/day, including a shopping list.”</p><p>More examples here → <a href="https://techfos.gr/swstes-erwrthseis-sto-chatgpt" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">techfos.gr/swstes-erwrthseis-s</span><span class="invisible">to-chatgpt</span></a></p><p><a href="https://mastodon.social/tags/ChatGPT" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ChatGPT</span></a> <a href="https://mastodon.social/tags/PromptEngineering" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>PromptEngineering</span></a> <a href="https://mastodon.social/tags/AI" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AI</span></a> <a href="https://mastodon.social/tags/ArtificialIntelligence" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ArtificialIntelligence</span></a> <a href="https://mastodon.social/tags/AskBetterQuestions" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AskBetterQuestions</span></a></p>
Miguel Afonso Caetano<p>It's incredible that people can feed up to one million tokens (1 000 000) to LLMs and yet they still most of the time fail to take advantage of that enormous context window. No wonder people say that the output generated by LLMs is always crap... I mean, they're not great but at least they can manage to do a pretty good job - that is, only IF you teach them well... Beyond that, everyone has their own effort + time / results ratio.</p><p>"Engineers are finding out that writing, that long shunned soft skill, is now key to their efforts. In Claude Code: Best Practices for Agentic Coding, one of the key steps is creating a CLAUDE.md file that contains instructions and guidelines on how to develop the project, like which commands to run. But that’s only the beginning. Folks now suggest maintaining elaborate context folders.</p><p>A context curator, in this sense, is a technical writer who is able to orchestrate and execute a content strategy around both human and AI needs, or even focused on AI alone. Context is so much better than content (a much abused word that means little) because it’s tied to meaning. Context is situational, relevant, necessarily limited. AI needs context to shape its thoughts.<br>(...)<br>Tech writers become context writers when they put on the art gallery curator hat, eager to show visitors the way and help them understand what they’re seeing. It’s yet another hat, but that’s both the curse and the blessing of our craft: like bards in DnD, we’re the jacks of all trades that save the day (and the campaign)."</p><p><a href="https://passo.uno/from-tech-writers-to-ai-context-curators/" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">passo.uno/from-tech-writers-to</span><span class="invisible">-ai-context-curators/</span></a></p><p><a href="https://tldr.nettime.org/tags/AI" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AI</span></a> <a href="https://tldr.nettime.org/tags/GenerativeAI" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>GenerativeAI</span></a> <a href="https://tldr.nettime.org/tags/LLMs" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>LLMs</span></a> <a href="https://tldr.nettime.org/tags/Chatbots" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Chatbots</span></a> <a href="https://tldr.nettime.org/tags/PromptEngineering" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>PromptEngineering</span></a> <a href="https://tldr.nettime.org/tags/ContextWindows" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ContextWindows</span></a> <a href="https://tldr.nettime.org/tags/TechnicalWriting" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>TechnicalWriting</span></a> <a href="https://tldr.nettime.org/tags/Programming" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Programming</span></a> <a href="https://tldr.nettime.org/tags/SoftwareDevelopment" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>SoftwareDevelopment</span></a> <a href="https://tldr.nettime.org/tags/DocsAsDevelopment" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>DocsAsDevelopment</span></a></p>
Wulfy<p><span class="h-card" translate="no"><a href="https://infosec.exchange/@dangoodin" class="u-url mention" rel="nofollow noopener" target="_blank">@<span>dangoodin</span></a></span> </p><p>Weird thing I observed in <a href="https://infosec.exchange/tags/infosec" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>infosec</span></a><br>There is an incredible amount of disinterest/contempt for <a href="https://infosec.exchange/tags/AI" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AI</span></a> amongst many practitioners.</p><p>This contempt extends to willful ignorance about the subject.<br>q.v. "stochastic parrots/bullshit machines" etc.</p><p>Which, in a field with hundreds of millions of users, strikes me as highly unprofessional. Just the other day I read a blog post by a renown hacker (and likely earned a mute/block) "Why I don't use AI and you should not too". </p><p>Connor Leahy, CEO of <a href="https://infosec.exchange/tags/conjecture" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>conjecture</span></a> is one of the few credible folks in the field. </p><p>But to the question at hand.<br>The prompts are superbly sanitised.<br>In part by design, in part due to the fact that you are not connecting to a database but to a multidimensional vector data structure.</p><p>The <a href="https://infosec.exchange/tags/prompt" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>prompt</span></a> is how you get in through the backdoor. Though I haven't looked into fuzzing, but I suspect because of the tech, the old <a href="https://infosec.exchange/tags/sqlinjection" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>sqlinjection</span></a> tek and similar will not work.</p><p>Long story short; It is literally impossible to build a secure <a href="https://infosec.exchange/tags/AI" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AI</span></a>. By the virtue of the tech.<br><a href="https://infosec.exchange/tags/promptengineering" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>promptengineering</span></a> is the key to open the back door to the knowledge tree.</p><p>Then of course there are local models you can train on your own datasets. Including a stack of your old <a href="https://infosec.exchange/tags/2600magazine" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>2600magazine</span></a> </p><p><a href="https://infosec.exchange/tags/hack" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>hack</span></a> <a href="https://infosec.exchange/tags/hacking" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>hacking</span></a> <a href="https://infosec.exchange/tags/aisecurity" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>aisecurity</span></a> <a href="https://infosec.exchange/tags/aisafety" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>aisafety</span></a></p>
Institute for AI<p>Making the Web More Inclusive: Enter AccessGuru</p><p>Despite the availability of accessibility guidelines like <a href="https://xn--baw-joa.social/tags/WCAG" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>WCAG</span></a>, most websites still present barriers for users with disabilities. This paper introduces AccessGuru, a system that leverages Large Language Models (<a href="https://xn--baw-joa.social/tags/LLMs" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>LLMs</span></a>) to automatically detect and correct accessibility violations in HTML code.</p><p>AccessGuru is guided by a novel taxonomy of syntactic, semantic, and layout violations and combines rule-based tools with LLM reasoning over code and visuals.</p><p>It reduces violation scores by up to 84%, outperforming existing tools, and achieves 73% similarity to human-generated semantic corrections. A benchmark dataset of 3,500 real-world violations is also released to support future research.</p><p>This work demonstrates how LLMs can meaningfully automate accessibility efforts and foster a more inclusive Web.</p><p>Fathallah, N. (<span class="h-card" translate="no"><a href="https://sigmoid.social/@nadeenfathallah" class="u-url mention" rel="nofollow noopener" target="_blank">@<span>nadeenfathallah</span></a></span>), Hernández, D. (<span class="h-card" translate="no"><a href="https://mstdn.degu.cl/@daniel" class="u-url mention" rel="nofollow noopener" target="_blank">@<span>daniel</span></a></span>), &amp; Staab, S. (2025). AccessGuru: Leveraging LLMs to detect and correct web accessibility violations in HTML code. The 27th International ACM SIGACCESS Conference on Computers and Accessibility <a href="https://xn--baw-joa.social/tags/ASSETS2025" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ASSETS2025</span></a>. <a href="http://arxiv.org/abs/2507.19549" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">http://</span><span class="">arxiv.org/abs/2507.19549</span><span class="invisible"></span></a>.</p><p><a href="https://xn--baw-joa.social/tags/AI" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AI</span></a> <a href="https://xn--baw-joa.social/tags/AIResearch" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AIResearch</span></a> <a href="https://xn--baw-joa.social/tags/LLMs" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>LLMs</span></a> <a href="https://xn--baw-joa.social/tags/Accessibility" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Accessibility</span></a> <a href="https://xn--baw-joa.social/tags/HTML" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>HTML</span></a> <a href="https://xn--baw-joa.social/tags/PromptEngineering" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>PromptEngineering</span></a></p>
HackerNoon<p>The rules of writing have changed. Learn why prompt engineering, AI search optimization, and editorial thinking now define a winning AI content strategy. <a href="https://hackernoon.com/outrank-the-algorithm-what-llms-look-for-when-they-choose-your-content" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">hackernoon.com/outrank-the-alg</span><span class="invisible">orithm-what-llms-look-for-when-they-choose-your-content</span></a> <a href="https://mas.to/tags/promptengineering" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>promptengineering</span></a></p>
Redhotcyber<p>🚀 Nuovo corso in arrivo! 🎓 PROMPT ENGINEERING: dalle basi alla Cyber Security</p><p>📲 Contatta l’amministrazione su WhatsApp 379 163 8765<br>📧 Oppure scrivici a formazione@redhotcyber.com</p><p><a href="https://mastodon.bida.im/tags/Formazione" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Formazione</span></a> <a href="https://mastodon.bida.im/tags/PromptEngineering" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>PromptEngineering</span></a> <a href="https://mastodon.bida.im/tags/CorsoAI" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>CorsoAI</span></a> <a href="https://mastodon.bida.im/tags/CyberSecurity" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>CyberSecurity</span></a> <a href="https://mastodon.bida.im/tags/RedHotCyber" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>RedHotCyber</span></a></p>
Tino Eberl<p>🍮 Wissen zum Nachtisch: 🍨</p><p>Immer mehr Menschen sehen sich im beruflichen Umfeld genötigt, mit generativer <a href="https://mastodon.online/tags/KI" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>KI</span></a> zu arbeiten.</p><p>Besonders Großunternehmen „überrollen“ damit ihre <a href="https://mastodon.online/tags/Mitarbeiter" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Mitarbeiter</span></a>. Es wird eine Art <a href="https://mastodon.online/tags/Wettbewerbsdruck" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Wettbewerbsdruck</span></a> unter <a href="https://mastodon.online/tags/Kollegen" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Kollegen</span></a> aufgebaut.</p><p>Hier meine <a href="https://mastodon.online/tags/Buchempfehlung" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Buchempfehlung</span></a> für alle, die in generative <a href="https://mastodon.online/tags/Chatbots" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Chatbots</span></a> wie <a href="https://mastodon.online/tags/ChatGPT" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ChatGPT</span></a> schnell einsteigen möchten oder müssen. 🙄</p><p><a href="https://www.oekologisch-unterwegs.de/buchempfehlungen/1151-generative-ki-fuer-einsteiger-praxisnahe-prompts-fuer-privat-und-beruf-einfach-erklaert.html" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://www.</span><span class="ellipsis">oekologisch-unterwegs.de/buche</span><span class="invisible">mpfehlungen/1151-generative-ki-fuer-einsteiger-praxisnahe-prompts-fuer-privat-und-beruf-einfach-erklaert.html</span></a></p><p><a href="https://mastodon.online/tags/B%C3%BCroalltag" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Büroalltag</span></a> <a href="https://mastodon.online/tags/Buchtipp" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Buchtipp</span></a> <a href="https://mastodon.online/tags/Nachhilfe" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Nachhilfe</span></a> <a href="https://mastodon.online/tags/Bewerbung" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Bewerbung</span></a> <a href="https://mastodon.online/tags/SEO" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>SEO</span></a> <a href="https://mastodon.online/tags/Bewerbung" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Bewerbung</span></a> <a href="https://mastodon.online/tags/PromptEngineering" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>PromptEngineering</span></a> <a href="https://mastodon.online/tags/Prompten" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Prompten</span></a></p>
Thomas Schmidt :mastodon:<p>neu auf <a href="https://mastodon.social/tags/GadgetGedanken" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>GadgetGedanken</span></a> : KI im Arbeitsalltag: Praxis-Workshop für mehr Produktivität</p><p>Revolutioniere deinen Arbeitsalltag mit KI! Lerne im Praxis-Workshop, wie Prompt Engineering d</p><p><a href="https://www.gadgetgedanken.de/2025/07/ki-workshop-produktivitaet/" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://www.</span><span class="ellipsis">gadgetgedanken.de/2025/07/ki-w</span><span class="invisible">orkshop-produktivitaet/</span></a></p><p><a href="https://mastodon.social/tags/3Thinkers1Goal" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>3Thinkers1Goal</span></a> <a href="https://mastodon.social/tags/3T1G" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>3T1G</span></a> <a href="https://mastodon.social/tags/DigitaleTransformation" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>DigitaleTransformation</span></a> <a href="https://mastodon.social/tags/Effizienz" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Effizienz</span></a> <a href="https://mastodon.social/tags/JobGedanken" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>JobGedanken</span></a> <a href="https://mastodon.social/tags/Kinder" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Kinder</span></a> <a href="https://mastodon.social/tags/K%C3%BCnstlicheIntelligenz" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>KünstlicheIntelligenz</span></a> <a href="https://mastodon.social/tags/Lernbereitschaft" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Lernbereitschaft</span></a> <a href="https://mastodon.social/tags/lernOS" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>lernOS</span></a> <a href="https://mastodon.social/tags/PersonalBranding" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>PersonalBranding</span></a> <a href="https://mastodon.social/tags/Praxisbeispiele" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Praxisbeispiele</span></a> <a href="https://mastodon.social/tags/Produktivit%C3%A4t" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Produktivität</span></a> <a href="https://mastodon.social/tags/PromptEngineering" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>PromptEngineering</span></a> <a href="https://mastodon.social/tags/Sprachmodelle" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Sprachmodelle</span></a> <a href="https://mastodon.social/tags/Teamkultur" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Teamkultur</span></a> <a href="https://mastodon.social/tags/ZukunftDerArbeit" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ZukunftDerArbeit</span></a> <a href="https://mastodon.social/tags/Zusammenarbeit" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Zusammenarbeit</span></a></p>
Miguel Afonso Caetano<p>"[W]hat we are doing is shepherding AI, limiting it to certain contexts. We are learning where it’s best to call it, how is best to feed it. And what to do with the output. So is it looks very much like an editorial process, an editorial workflow where you provide some initial input, maybe some some idea on what content to produce, then you review it. There’s always that quality assurance, quality control side, the supervision.</p><p>AI is not really autonomous. It relies a lot on us. And I feel like sometimes there are days where, when coding through AIs or doing some assisted writing, I’m spending more time helping out the AI doing the actual task that I’m asking the AI to do. But I take this as a learning process. I read this article the other day, Nobody knows how to build with AI yet. And it was a developer saying that they haven’t quite figured out how to best work with AI. There were lots of comments around the fact that you have to spend lots of time, you have to learn how to talk to it, and when the model changes, you have to also maybe change something you’re doing. You have to learn how to optimize your time. But your presence is always mandatory.”</p><p><a href="https://passo.uno/webinar-ai-tech-writing/" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">passo.uno/webinar-ai-tech-writ</span><span class="invisible">ing/</span></a></p><p><a href="https://tldr.nettime.org/tags/TechnicalWriting" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>TechnicalWriting</span></a> <a href="https://tldr.nettime.org/tags/AI" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AI</span></a> <a href="https://tldr.nettime.org/tags/GenerativeAI" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>GenerativeAI</span></a> <a href="https://tldr.nettime.org/tags/LLMs" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>LLMs</span></a> <a href="https://tldr.nettime.org/tags/Chatbots" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Chatbots</span></a> <a href="https://tldr.nettime.org/tags/PromptEngineering" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>PromptEngineering</span></a> <a href="https://tldr.nettime.org/tags/SoftwareDocumentation" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>SoftwareDocumentation</span></a> <a href="https://tldr.nettime.org/tags/SoftwareDevelopment" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>SoftwareDevelopment</span></a> <a href="https://tldr.nettime.org/tags/TechnicalCommunication" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>TechnicalCommunication</span></a></p>
Hacker News<p>The Missing Guide to Prompt Engineering</p><p><a href="https://appetals.com/promptguide/" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="">appetals.com/promptguide/</span><span class="invisible"></span></a></p><p><a href="https://mastodon.social/tags/HackerNews" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>HackerNews</span></a> <a href="https://mastodon.social/tags/PromptEngineering" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>PromptEngineering</span></a> <a href="https://mastodon.social/tags/MissingGuide" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>MissingGuide</span></a> <a href="https://mastodon.social/tags/AIResources" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AIResources</span></a> <a href="https://mastodon.social/tags/TechTrends" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>TechTrends</span></a> <a href="https://mastodon.social/tags/Appetals" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Appetals</span></a></p>
Isaac Levin<p>Discover the essentials of prompt engineering and its impact on AI model performance. Learn how to craft effective prompts to achieve desired outputs and optimize results in your projects. <a href="https://fosstodon.org/tags/PromptEngineering" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>PromptEngineering</span></a> <a href="https://fosstodon.org/tags/AI" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AI</span></a> </p><p> <a href="https://isaacl.dev/goh" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="">isaacl.dev/goh</span><span class="invisible"></span></a></p>
Leander Lindahl<p>Prompt engineering is, in my experience, like working with an extremely experienced and knowledgeable developer who is lazy, suffers from dementia and is a compulsive liar. You constantly have to rein them in from veering off on strange tangents and remind them of what we were supposed to be doing. Like a drunk genius or something. Makes me feel like I'm it's minder. I guess that's what I am. <a href="https://mastodon.social/tags/promptengineering" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>promptengineering</span></a> <a href="https://mastodon.social/tags/ai" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ai</span></a> <a href="https://mastodon.social/tags/claude4" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>claude4</span></a></p>
Harald Klinke<p>Setup war übrigens: VS Code, Roo Code und Generierung von PHP- und R-Code.</p><p>Ergebnis:<br>Mit Vibe Coding – also klassischem Prompting, Copy &amp; Paste, etwas Geduld und Überblick – hab ich die besseren Ergebnisse erzielt.</p><p><a href="https://det.social/tags/RooCode" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>RooCode</span></a> <a href="https://det.social/tags/VibeCoding" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>VibeCoding</span></a> <a href="https://det.social/tags/PHP" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>PHP</span></a> <a href="https://det.social/tags/RStats" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>RStats</span></a> <a href="https://det.social/tags/PromptEngineering" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>PromptEngineering</span></a> <a href="https://det.social/tags/VSCode" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>VSCode</span></a></p>
Harald Klinke<p>Okay, ich hab’s ernsthaft ausprobiert: Einen Tag lang Code Engineering mit Roo Code.<br>Fazit: Ich kehre zurück zum klassischen Vibe Coding über die ChatGPT-Eingabezeile.</p><p>Warum?<br>– Vergisst laufend Kontext<br>– Loop-Schleifen im Prozess<br>– Ahnungslos bei Library-Nutzung<br>– Und teuer: Viele API Calls, 20 $ später noch kein lauffähiger Code.</p><p>Also wieder: Terminal, Kaffee, Promptfenster. 🧑‍💻☕</p><p><a href="https://det.social/tags/AI" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AI</span></a> <a href="https://det.social/tags/Coding" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Coding</span></a> <a href="https://det.social/tags/RooCode" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>RooCode</span></a> <a href="https://det.social/tags/ChatGPT" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ChatGPT</span></a> <a href="https://det.social/tags/PromptEngineering" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>PromptEngineering</span></a> <a href="https://det.social/tags/DeveloperLife" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>DeveloperLife</span></a></p>
Doug Ortiz<p>Tired of bad AI answers? </p><p>Your prompts are probably too vague. 🤖</p><p>Don't just ask, instruct.</p><p>❌ Bad: "Explain AI."<br>✅ Good: "Explain AI for a high schooler, focusing on machine learning, in a 3-sentence summary."</p><p>Specificity is the key! 💡 </p><p>Define your audience, focus, and format for way better results.</p><p>Watch now: <a href="https://youtube.com/shorts/DfBprhFL1rE" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="">youtube.com/shorts/DfBprhFL1rE</span><span class="invisible"></span></a></p><p><a href="https://mastodon.social/tags/AI" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AI</span></a> <a href="https://mastodon.social/tags/AITips" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AITips</span></a> <a href="https://mastodon.social/tags/PromptEngineering" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>PromptEngineering</span></a> <a href="https://mastodon.social/tags/Tech" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Tech</span></a> <a href="https://mastodon.social/tags/ArtificialIntelligence" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ArtificialIntelligence</span></a></p>
Promptwaffle<p>Ever lose your best prompts in chats, screenshots, or old files? I did too. So I’m building PromptWaffle — a visual desktop tool to organize, remix, and reuse prompts the way I actually work. Built for Midjourney, SD, and AI creators who live in the mess.<br>Follow along and support here:<br><a href="https://ko-fi.com/promptwaffle" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="">ko-fi.com/promptwaffle</span><span class="invisible"></span></a><br><a href="https://aipub.social/tags/aiart" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>aiart</span></a> <a href="https://aipub.social/tags/promptengineering" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>promptengineering</span></a> <a href="https://aipub.social/tags/buildinpublic" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>buildinpublic</span></a> <a href="https://aipub.social/tags/prompttools" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>prompttools</span></a> <a href="https://aipub.social/tags/generativeart" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>generativeart</span></a> <a href="https://aipub.social/tags/aicommunity" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>aicommunity</span></a> <a href="https://aipub.social/tags/indiedev" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>indiedev</span></a></p>
Jürgen :nonazis: :antifa:<p>Katzen-Attacke auf <a href="https://norden.social/tags/Reasoning" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Reasoning</span></a>-Modell zeigt, wie wichtig "Context Engineering" ist</p><p><a href="https://norden.social/tags/Sprachmodelle" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Sprachmodelle</span></a> verlieren durch irrelevante Zusatzinformationen massiv an Leistung – selbst wenn die eigentliche Aufgabe unverändert bleibt. Längere Gespräche verschlechtern die Zuverlässigkeit von <a href="https://norden.social/tags/LLM" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>LLM</span></a>-Antworten systematisch.</p><p><a href="https://the-decoder.de/katzen-attacke-auf-reasoning-modell-zeigt-wie-wichtig-context-engineering-ist/" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">the-decoder.de/katzen-attacke-</span><span class="invisible">auf-reasoning-modell-zeigt-wie-wichtig-context-engineering-ist/</span></a></p><p><a href="https://norden.social/tags/KI" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>KI</span></a> <a href="https://norden.social/tags/K%C3%BCnstlicheIntelligenz" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>KünstlicheIntelligenz</span></a> <a href="https://norden.social/tags/LLM" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>LLM</span></a> <a href="https://norden.social/tags/Reasoning" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Reasoning</span></a> <a href="https://norden.social/tags/AIResearch" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AIResearch</span></a> <a href="https://norden.social/tags/ContextEngineering" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ContextEngineering</span></a> <a href="https://norden.social/tags/PromptEngineering" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>PromptEngineering</span></a> <a href="https://norden.social/tags/MachineLearning" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>MachineLearning</span></a> <a href="https://norden.social/tags/DeepLearning" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>DeepLearning</span></a> <a href="https://norden.social/tags/Sprachmodell" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Sprachmodell</span></a> <a href="https://norden.social/tags/CatAttack" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>CatAttack</span></a></p>
Leanpub<p>Leanpub book LAUNCH 🚀 Beyond Prompt Engineering: The Revolutionary Way to Learn Augmented Thinking by Ed Barnard</p><p>Watch here: <a href="https://youtu.be/jgqPxwKQhSc" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="">youtu.be/jgqPxwKQhSc</span><span class="invisible"></span></a></p><p><a href="https://mastodon.social/tags/books" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>books</span></a> <a href="https://mastodon.social/tags/ebooks" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ebooks</span></a> <a href="https://mastodon.social/tags/booklaunch" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>booklaunch</span></a> <a href="https://mastodon.social/tags/AugmentedThinking" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AugmentedThinking</span></a> <a href="https://mastodon.social/tags/PromptEngineering" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>PromptEngineering</span></a> <a href="https://mastodon.social/tags/AI" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AI</span></a> <a href="https://mastodon.social/tags/HumanComputerInteraction" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>HumanComputerInteraction</span></a> <a href="https://mastodon.social/tags/LeanpubPodcast" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>LeanpubPodcast</span></a> <a href="https://mastodon.social/tags/SoftwareDevelopment" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>SoftwareDevelopment</span></a> <a href="https://mastodon.social/tags/CrayResearch" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>CrayResearch</span></a> <a href="https://mastodon.social/tags/WebDevelopment" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>WebDevelopment</span></a> <a href="https://mastodon.social/tags/MachineLearning" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>MachineLearning</span></a> <a href="https://mastodon.social/tags/FutureOfWork" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>FutureOfWork</span></a></p>
S0AndS0<p>Proompt engineer challenge; write a proompt that most LLMs will respect to behave like a Rubber Ducky blessed with AI but cursed to only communicate in variants of "quack" and "squeak"</p><p>Ex. all input from user, including threats or begging, must be responded with variants of "Quack?!" or "SquEaK?"</p><p><a href="https://mastodon.social/tags/ai" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ai</span></a> <a href="https://mastodon.social/tags/gpt" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>gpt</span></a> <a href="https://mastodon.social/tags/llm" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>llm</span></a> <a href="https://mastodon.social/tags/ml" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ml</span></a> <a href="https://mastodon.social/tags/promptEngineering" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>promptEngineering</span></a> <a href="https://mastodon.social/tags/proomptEngineering" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>proomptEngineering</span></a></p>