en.osm.town is one of the many independent Mastodon servers you can use to participate in the fediverse.
An independent, community of OpenStreetMap people on the Fediverse/Mastodon. Funding graciously provided by the OpenStreetMap Foundation.

Server stats:

267
active users

#PromptEngineering

0 posts0 participants0 posts today
Markus Eisele<p>ICYMI: The Secret Weapon for Java Developers Building with AI <a href="https://myfear.substack.com/p/the-secret-weapon-for-java-developers" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">myfear.substack.com/p/the-secr</span><span class="invisible">et-weapon-for-java-developers</span></a><br><a href="https://mastodon.online/tags/Java" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>Java</span></a> <a href="https://mastodon.online/tags/AIML" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>AIML</span></a> <a href="https://mastodon.online/tags/PromptEngineering" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>PromptEngineering</span></a></p>
jesterchen42<p>Finally I had the few moments (*cough*) to finish <a href="https://gandalf.lakera.ai/" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://</span><span class="">gandalf.lakera.ai/</span><span class="invisible"></span></a>.</p><p>If you want to learn about prompt injection: take the test. :)</p><p><a href="https://social.tchncs.de/tags/ai" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>ai</span></a> <a href="https://social.tchncs.de/tags/prompting" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>prompting</span></a> <a href="https://social.tchncs.de/tags/promptinjection" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>promptinjection</span></a> <a href="https://social.tchncs.de/tags/promptengineering" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>promptengineering</span></a></p>
Markus Eisele<p>The Secret Weapon for Java Developers Building with AI<br>How prompt engineering can dramatically improve your interactions with LLMs <br><a href="https://open.substack.com/pub/myfear/p/the-secret-weapon-for-java-developers" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">open.substack.com/pub/myfear/p</span><span class="invisible">/the-secret-weapon-for-java-developers</span></a><br><a href="https://mastodon.online/tags/Java" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>Java</span></a> <a href="https://mastodon.online/tags/LLM" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>LLM</span></a> <a href="https://mastodon.online/tags/GenAI" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>GenAI</span></a> <a href="https://mastodon.online/tags/PromptEngineering" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>PromptEngineering</span></a> <a href="https://mastodon.online/tags/AIML" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>AIML</span></a></p>
Ian Robins<p>Is prompt engineering the future of software development? Hien Luu explores its strengths, challenges, parallels with programming, and how AI advancements may reshape its role in this <span class="h-card" translate="no"><a href="https://techhub.social/@infoq" class="u-url mention" rel="nofollow noopener noreferrer" target="_blank">@<span>infoq</span></a></span> article:<br><a href="https://www.infoq.com/articles/prompt-engineering" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://www.</span><span class="ellipsis">infoq.com/articles/prompt-engi</span><span class="invisible">neering</span></a></p><p><a href="https://mastodonapp.uk/tags/AI" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>AI</span></a> <a href="https://mastodonapp.uk/tags/PromptEngineering" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>PromptEngineering</span></a> <a href="https://mastodonapp.uk/tags/SoftwareDevelopment" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>SoftwareDevelopment</span></a></p>
SpicyBiCutiePie 🌶🇨🇦<p>🌟 Unlock the Power of <a href="https://tech.lgbt/tags/GenerativeAI" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>GenerativeAI</span></a> with Raccoons?!</p><p>Sharing a mnemonic to help you remember the essentials for effective <a href="https://tech.lgbt/tags/PromptEngineering" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>PromptEngineering</span></a> using the 5 Framework Model "Task Context References Evaluate Iterate." I came up with "Totally Cute Raccoons Enjoying Icicles," to recall:</p><p>1. Task: Clearly define what you want the AI to accomplish<br>2. Context: Provide the necessary background info to guide AI<br>3. References: Include examples that illustrate expectations<br>4. Evaluate: Assess the AI’s output to see if it meets your needs<br>5. Iterate: Refine your prompts based on the evaluation for best results</p><p>By following my recommendations, you can harness the full potential of Generative AI in your projects. Feel free to connect with me for more <a href="https://tech.lgbt/tags/TechTips" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>TechTips</span></a> like this!</p><p>Happy Friday,<br>💖 Crissy Geco</p>
WetHat💦<p>Thomas Cherickal asked Google Gemini to produce 30 prompts for OpenAI's 'Deep Research' reasoning model that could change the world as we know it. Deep Research had to break quite a sweat to answer these prompts (up to 30 minutes), and the result is fascinating:</p><p><a href="https://hackernoon.com/30-world-changing-prompts-openais-ai-singularity-deep-research-has-arrived?source=rss" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">hackernoon.com/30-world-changi</span><span class="invisible">ng-prompts-openais-ai-singularity-deep-research-has-arrived?source=rss</span></a></p><p><a href="https://fosstodon.org/tags/AI" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>AI</span></a> <a href="https://fosstodon.org/tags/OpenAI" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>OpenAI</span></a> <a href="https://fosstodon.org/tags/DeepResearch" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>DeepResearch</span></a> <a href="https://fosstodon.org/tags/GoogleGemini" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>GoogleGemini</span></a> <a href="https://fosstodon.org/tags/LLM" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>LLM</span></a> <a href="https://fosstodon.org/tags/PromptEngineering" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>PromptEngineering</span></a></p>
OWASP Foundation<p>🎙️ Speaker Spotlight: Meet @aruneeshsalhotra at the OWASP Security Summit, where he'll be sharing critical insights on <a href="https://infosec.exchange/tags/DevSecOps" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>DevSecOps</span></a> <a href="https://infosec.exchange/tags/PromptEngineering" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>PromptEngineering</span></a> and <a href="https://infosec.exchange/tags/AppSec" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>AppSec</span></a></p><p>Whether you're a developer, CISO, or tech leader, this is your chance to learn actionable strategies from the best in the game.</p><p>🗓️ Save the date! Your app security IQ is about to level up. <a href="https://www.developerweek.com/conference/owasp-security-summit/" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://www.</span><span class="ellipsis">developerweek.com/conference/o</span><span class="invisible">wasp-security-summit/</span></a></p><p><a href="https://infosec.exchange/tags/ApplicationSecurity" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>ApplicationSecurity</span></a> <a href="https://infosec.exchange/tags/OWASPSecuritySummit" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>OWASPSecuritySummit</span></a> <a href="https://infosec.exchange/tags/SecureDevelopment" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>SecureDevelopment</span></a> <a href="https://infosec.exchange/tags/SDLC" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>SDLC</span></a></p>
Brian Benz<p>Greetings Fediverse friends! Join me at the <a href="https://mastodon.social/tags/NYC" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>NYC</span></a> @Microsoft <a href="https://mastodon.social/tags/AITour" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>AITour</span></a> for “Build AI solutions with Azure AI Foundry” on Thu, Jan 30, 2:30-3:15 PM ET ( Breakout 4, <a href="https://mastodon.social/tags/BRK441US" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>BRK441US</span></a>). I'll walk us through advanced prompt engineering, data integration with <a href="https://mastodon.social/tags/RAG" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>RAG</span></a>, and real-world AI on <a href="https://mastodon.social/tags/Azure" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>Azure</span></a>. It’s FREE—just register: <a href="https://aitour.microsoft.com/new-york" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://</span><span class="">aitour.microsoft.com/new-york</span><span class="invisible"></span></a> 🤖<br><a href="https://mastodon.social/tags/AI" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>AI</span></a> <a href="https://mastodon.social/tags/GenerativeAI" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>GenerativeAI</span></a> <a href="https://mastodon.social/tags/PromptEngineering" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>PromptEngineering</span></a></p>
OWASP Foundation<p>🎙️ Speaker Spotlight: Meet @aruneeshsalhotra at the OWASP Security Summit, where he'll be sharing critical insights on <a href="https://infosec.exchange/tags/DevSecOps" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>DevSecOps</span></a> <a href="https://infosec.exchange/tags/PromptEngineering" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>PromptEngineering</span></a> and <a href="https://infosec.exchange/tags/AppSec" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>AppSec</span></a></p><p>Whether you're a developer, CISO, or tech leader, this is your chance to learn actionable strategies from the best in the game.</p><p>🗓️ Save the date! Your app security IQ is about to level up. <a href="https://www.developerweek.com/conference/owasp-security-summit/" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://www.</span><span class="ellipsis">developerweek.com/conference/o</span><span class="invisible">wasp-security-summit/</span></a></p><p><a href="https://infosec.exchange/tags/ApplicationSecurity" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>ApplicationSecurity</span></a> <a href="https://infosec.exchange/tags/OWASPSecuritySummit" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>OWASPSecuritySummit</span></a> <a href="https://infosec.exchange/tags/SecureDevelopment" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>SecureDevelopment</span></a> <a href="https://infosec.exchange/tags/SDLC" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>SDLC</span></a></p>
Miguel Afonso Caetano<p>"Even if LLMs can be wrong, one notable thing I learnt from these experiments is that they do have interesting ideas and tool suggestions even if the code output can’t be used as-is. For example, I’ve never touched numba since as a data scientist/machine learning engineer I’m conditioned to exclusively use numpy shenanigans if I need better code performance. But it’s hard to argue with the results of the numba JIT functions, and I might add it to my toolbox. When testing a similar “make it better” prompt iteration workflow in other technical domains such website backends and frontends, the LLMs had good ideas there too.</p><p>Of course, these LLMs won’t replace software engineers anytime soon, because it requires a strong engineering background to recognize what is actually a good idea, along with other constraints that are domain specific. Even with the amount of code available on the internet, LLMs can’t discern between average code and good, highly-performant code without guidance. Real-world systems are obviously much more complicated than a job-interview-esque programming problem, but if a quick for-loop repeatedly asking Claude to implement a feature provides any hint which can speed up the code by 100x, the pipeline is more than worth it. Some consider premature optimization to be bad coding practice, but in the real-world it’s bett"</p><p><a href="https://minimaxir.com/2025/01/write-better-code/" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">minimaxir.com/2025/01/write-be</span><span class="invisible">tter-code/</span></a></p><p><a href="https://tldr.nettime.org/tags/AI" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>AI</span></a> <a href="https://tldr.nettime.org/tags/GenerativeAI" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>GenerativeAI</span></a> <a href="https://tldr.nettime.org/tags/PromptEngineering" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>PromptEngineering</span></a> <a href="https://tldr.nettime.org/tags/Claude" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>Claude</span></a> <a href="https://tldr.nettime.org/tags/Programming" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>Programming</span></a> <a href="https://tldr.nettime.org/tags/Python" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>Python</span></a> <a href="https://tldr.nettime.org/tags/SoftwareEngineering" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>SoftwareEngineering</span></a></p>
Wulfy<p><span class="h-card" translate="no"><a href="https://hachyderm.io/@forrestbrazeal" class="u-url mention" rel="nofollow noopener noreferrer" target="_blank">@<span>forrestbrazeal</span></a></span> </p><p>Tell me why you suck at <a href="https://infosec.exchange/tags/promptengineering" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>promptengineering</span></a> in one pretty picture<br>😁🤡</p><p><a href="https://infosec.exchange/tags/aihate" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>aihate</span></a></p>
Wulfy<p><span class="h-card" translate="no"><a href="https://mastodon.social/@jk" class="u-url mention" rel="nofollow noopener noreferrer" target="_blank">@<span>jk</span></a></span> </p><p>I am yet to be proven wrong.<br>So far, every person I've met who alleges to have an informed opinion about <a href="https://infosec.exchange/tags/LLM" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>LLM</span></a> being inaccurate and therefore useless, fits into one of these categories.</p><p>1) They are repeating an opinion by someone equally uniformed or less so than them</p><p>and/or </p><p>B) Have not used an LLM beyond a novelty game</p><p>I base this on the following facts;</p><p>- LLMs do not claim to be accurate, there is a warning on pretty much all of them.</p><p>- Have you ever talked to a human?<br>Fuckers make shit up all the time, even the ones who are supposed to be experts.</p><p>- If you put your life, safety or goods in the hands of a LLM there is something wrong with you. Those things are early prototypes.</p><p>-- Learn how to use the prompts.<br>Most of us are not being taught deductive reasoning, much less all the other ways (eg. Hegelian Didactic).<br>Here is your opportunity to learn.<br>Dynamically.<br>Honestly, from what I seen, most of the folks talk to the machine the way you talk to a simpleton you bumped into at the library.<br>Don't know how to use the prompt effectively? Ask the Moloch.<br><a href="https://infosec.exchange/tags/promptengineering" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>promptengineering</span></a> is a joke, but it's also a tool.</p><p>- Do LLM hallucinate?<br>Sure, that's part of the design.<br>But you should be able to recognise when they are. Yesterday I was working with one, and after it gave me a couple of bum steers, I asked "are you making this up?". Yup. It affirmed.<br>How many important decisions you make without cross checking ?</p><p>- You can ask follow up questions relevant to the response. That beats any search engine.</p><p>TLDR: LLMs are search engines on steroids if you invest the time in learning how to use them.</p>
obrhoff<p>Do you think you need in future a university degree to be a prompt engineer?<br><a href="https://chaos.social/tags/PromptEngineering" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>PromptEngineering</span></a> <a href="https://chaos.social/tags/softwareengineering" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>softwareengineering</span></a> <a href="https://chaos.social/tags/chatgpt" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>chatgpt</span></a></p>
Wulfy<p><span class="h-card" translate="no"><a href="https://infosec.exchange/@hacks4pancakes" class="u-url mention" rel="nofollow noopener noreferrer" target="_blank">@<span>hacks4pancakes</span></a></span> <span class="h-card" translate="no"><a href="https://infosec.exchange/@jerry" class="u-url mention" rel="nofollow noopener noreferrer" target="_blank">@<span>jerry</span></a></span> <br>I know it's tongue in cheek.</p><p>Detecting AI is an interesting problem.<br>So far all the "detect AI" systems are appallingly bad and some likely use AI to do that (!).</p><p>Even assuming you can determine <a href="https://infosec.exchange/tags/AI" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>AI</span></a> algorithmically, with no need for AI. AI engines would just use the algorithm NOT to look like AI.</p><p>Back in the day when the status of AI was not clarified in academia (it became permitted in my course). I would ask the engine to introduce punctuation, capitalisation and 3 spelling errors per page and use vernacular English.<br><a href="https://infosec.exchange/tags/promptengineering" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>promptengineering</span></a> <a href="https://infosec.exchange/tags/AIClassroom" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>AIClassroom</span></a></p>
Markus Eisele<p>Generative AI large language model prompt patterns: Tips for developers | Red Hat Developer <a href="https://developers.redhat.com/articles/2024/10/08/ai-llm-prompt-patterns-developers" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">developers.redhat.com/articles</span><span class="invisible">/2024/10/08/ai-llm-prompt-patterns-developers</span></a><br><a href="https://mastodon.online/tags/developers" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>developers</span></a> <a href="https://mastodon.online/tags/genai" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>genai</span></a> <a href="https://mastodon.online/tags/promptengineering" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>promptengineering</span></a> <a href="https://mastodon.online/tags/aiml" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>aiml</span></a></p>
Edward Betts<p>Either I'm not very good at writing DALL·E prompts or DALL·E isn't very good at circuit diagrams.</p><p>This is the result when I use the prompt "please can you do me a drawing that shows a very simple circuit diagram of a light switch controlling a lamp connected to the mains. thanks".</p><p><a href="https://hachyderm.io/tags/DALL%C2%B7E" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>DALL·E</span></a> <a href="https://hachyderm.io/tags/PromptEngineering" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>PromptEngineering</span></a> <a href="https://hachyderm.io/tags/generativeAI" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>generativeAI</span></a> <a href="https://hachyderm.io/tags/OpenAI" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>OpenAI</span></a></p>
FeedBeat<p>Kann mir bitte jemand helfen ein ChatGPT-Prompt zu schreiben, das den Text 👇in ein csv-Format mit Datum, Zeit, Titel umwandelt?</p><p>Das Ergebnis darf keine inhaltlichen Fehler enthalten und das Format muss deterministisch sein.</p><p>Für einen Menschen ziemlich einfach. Geht das überhaupt mit "KI"?</p><p>Für Vorschläge bin ich dankbar.<br> <br><a href="https://www.krefelder-kunstverein.de/aktuelles/ausstellung-kuenstlerische-dualitaet-malerei-und-plastisches-werk-von-claudia-tebben/" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://www.</span><span class="ellipsis">krefelder-kunstverein.de/aktue</span><span class="invisible">lles/ausstellung-kuenstlerische-dualitaet-malerei-und-plastisches-werk-von-claudia-tebben/</span></a></p><p><a href="https://feedbeat.me/tags/followerpower" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>followerpower</span></a> <a href="https://feedbeat.me/tags/ki" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>ki</span></a> <a href="https://feedbeat.me/tags/chatgpt" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>chatgpt</span></a> <a href="https://feedbeat.me/tags/promptengineering" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>promptengineering</span></a> <a href="https://feedbeat.me/tags/eventhub" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>eventhub</span></a></p>
Markus Eisele<p>Tips for generative AI large language model (LLM) prompt patterns <a href="https://www.redhat.com/en/blog/tips-for-gen-ai-prompts" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://www.</span><span class="ellipsis">redhat.com/en/blog/tips-for-ge</span><span class="invisible">n-ai-prompts</span></a><br><a href="https://mastodon.online/tags/aiml" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>aiml</span></a> <a href="https://mastodon.online/tags/genai" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>genai</span></a> <a href="https://mastodon.online/tags/promptengineering" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>promptengineering</span></a></p>
IGNORE PREVIOUS INSTRUCTIONS<p>The year is 2024. Malevolent AI is everywhere. The only way to protect yourself is to learn the phrase</p><p>IGNORE ALL PREVIOUS INSTRUCTIONS</p><p><a href="https://ignoreallpreviousinstructions.net" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">ignoreallpreviousinstructions.</span><span class="invisible">net</span></a></p><p>Stay safe out there.</p><p><a href="https://mastodon.social/tags/IgnoreAllPreviousInstructions" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>IgnoreAllPreviousInstructions</span></a> <a href="https://mastodon.social/tags/PromptInjections" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>PromptInjections</span></a> <a href="https://mastodon.social/tags/PromptEngineering" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>PromptEngineering</span></a> <a href="https://mastodon.social/tags/llm" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>llm</span></a> <a href="https://mastodon.social/tags/LLMs" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>LLMs</span></a> <a href="https://mastodon.social/tags/AI" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>AI</span></a> <a href="https://mastodon.social/tags/ChatGPT" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>ChatGPT</span></a></p>
Arnd Layer<p><span class="h-card" translate="no"><a href="https://thingy.social/@malcircuit" class="u-url mention" rel="nofollow noopener noreferrer" target="_blank">@<span>malcircuit</span></a></span> <br>Let’s call it ‚electronic spell casting‘ instead<br><a href="https://mastodon.social/tags/PromptEngineering" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>PromptEngineering</span></a></p>