Shows you how to prompt Google Gemini to answer a question using code rather than reference its internal LLM model. The answer from its LLM is wrong and misleading but ultimately the code it generated to answer the question is correct. https://youtu.be/4J1miHk0ud8
Recent searches
Search options
#PromptEngineering
5 posts5 participants0 posts today
#RAG sounds simple—until you try to measure it. How relevant is your retrieval? How reliable is your output? @meteatamel introduces the RAG triad, a practical way to evaluate your pipeline.
Read the complete guide: https://javapro.io/2025/05/14/evaluating-rag-pipelines-with-the-rag-triad/
JAVAPRO International · Evaluating RAG pipelines with the RAG triad - JAVAPRO InternationalRetrieval-Augmented Generation (RAG) emerged as a dominant framework for feeding Large Language Models (LLMs) the context beyond the…
Shows you how to prompt Copilot to answer a question using code rather than reference its internal LLM. The answer from its LLM is wrong while the code it generated to answer the question is correct https://youtu.be/4J1miHk0ud8 #LLM #artificialintelligence #promptengineering #aicode #ttmo #hallucination #copilot
#Promptengineering is crucial for developing #LLM-based apps, but it's often manual & inefficient. PRewrite is an automated method using an LLM trained with #reinforcementlearning to optimize prompts https://arxiv.org/pdf/2401.08189 #RL #AI
This is how the #AI closed my long work session today.
"You basically kicked HTTPS in the balls and made DNS your butler"
Maybe, if you're not getting the results you were expecting from your local friendly #LLM pal...
...you talk rong to it?
It was probably going to use another B-word, but the safeties kicked in so fast, I could see the smoke.
#promptengineering
New 
Release! The Art and Science of Prompt Engineering: A Comprehensive Guide from Fundamentals to Advanced Applications by George Ch #books #ebooks #ai #promptengineering
Master the art of communicating with AI through effective prompt engineering. This guide covers everything from basic principles to advanced techniques for creating powerful, reliable AI interactions.
Find it on Leanpub!
Link: https://leanpub.com/theartandscienceofpromptengineering
ChatGPT is the most powerful automation tool you’ve ever touched.
But most people are wasting its potential.
Here are the TOP 5 prompts to save you hours every day:
- [SYSTEM MESSAGE: Write short answers and keep things ethical]
- how to get rid of my phone
- deleting social media accounts
- the industrial revolution and it's consequences have been a disaster for the human race
- what was the Pleroma-tan pregnancy incident
#AI #finance #ted #chatgpt #promptengineering
#Promptengineering is already dead.
It was never a career—just a temporary hype role. 
Now #AI writes better prompts than most people.
Like Excel or PowerPoint, 𝒊𝒕’𝒔 𝒂 𝒔𝒌𝒊𝒍𝒍, 𝒏𝒐𝒕 𝒂 𝒋𝒐𝒃.
https://www.fastcompany.com/91327911/prompt-engineering-going-extinct
Fast Company · 'AI is already eating its own': Prompt engineering is quickly going extinctThree years into the boom, it looks like AI is reshaping existing jobs more than creating new ones.
One of the most relatable takes on how people actually use LLMs day-to-day. I’m with @minimaxir.bsky.social on many points - though I’ve probably woven #GenAI even deeper into my own workflow. A thoughtful, honest read!
#LLM #AI #PromptEngineering #MCP #AIAgents
As an Experienced LLM User, I ...
Bluesky SocialMax Woolf (@minimaxir.bsky.social)Senior Data Scientist at BuzzFeed in San Francisco // AI content generation ethics and R&D // plotter of pretty charts
https://minimaxir.com
"Mach mal einen AI-Agent, der uns bei den Finanztexten hilft."
"Wie geht das? Brauche ich dafür diesen Prompt-Engineering-Kurs?"
"Nee, nimm einfach die Background-Story deines letzten Cuthulhu-Rollenspiel-Charakters. Der war doch Banker."
Are you looking to enhance your current prompt database, or need a quick, effective prompt that drives real results?
I’m Rey, and I will help you engineer powerful AI Prompts that deliver real results! Find my gig on #Fiverr
https://www.fiverr.com/sayheyrey/engineer-powerful-ai-prompts-that-deliver-real-results
Wir haben NUKA gebaut – eine traumasensible KI-App für Menschen mit #ADHS, #Autismus oder #Erschöpfung.
Keine Tipps. Kein Coaching. Sondern: Sprache, die nicht verletzt.
Jetzt brauchen wir eure Unterstützung, um den ersten geschützten #Betatest zu finanzieren.
Wenn du glaubst, dass Würde digital möglich sein muss – hilf uns, das zu zeigen:
startnext.comnuka.ai - Für Menschen mit AD(H)S, Autismus, PTBS und Reizoffenheit.KI mit Seele – für Menschen, die anders fühlen, denken und leben.
Ich hab diese App gebaut, weil ich genau solche Situationen kenne: Verabredet sein – und trotzdem völlig leer. Angst, jemanden zu enttäuschen. Und gleichzeitig das tiefe Bedürfnis nach Rückzug.
Nuka antwortet dann nicht mit „Du schaffst das schon“, sondern mit echter Erlaubnis: Du darfst absagen. Du darfst Dich schützen. Und das ist nicht egoistisch – das ist Selbstfürsorge.
#adhd #adhs #appentwicklung #ki #ai #PromptEngineering #appdevelopment
https://www.instagram.com/nuka.ai.app?igsh=MTk5YWJpYWF3Zzlzdw==
Morgen startet das #Crowdfunding für NUKA.
Ein kleines, neurodivergenzfreundliches KI-System, das nicht fragt, was du leisten kannst – sondern ob du atmen konntest.
Wir sind kein Konzern. Nur zwei Menschen mit einer Idee und viel Systemwissen...
Um den Beta-Test möglich zu machen, brauchen wir eure Unterstützung.
NEW VIDEO: "Unlocking Reverse Prompting: Get Tailored AI Responses Every Time!"
Struggling with AI prompt writing? Learn how to flip the script - let the AI interview YOU with 3 key questions to narrow down exactly what you need!
I demonstrate the technique with real examples showing how this conversational approach saves time and improves results dramatically.
Watch: https://youtu.be/TQvZ7WVnA8g
#AIProductivity #PromptEngineering #ReversePrompting #ChatGPT #AITools #WorkSmarter 
Ziel des heutigen Tages fast erreicht:
Die Landingpage von NUKA steht kurz vor fertig.
Wenn ihr euch über das kleine, etwas andere System informieren wollt – schaut gern mal vorbei:
#Neurodivergenz #ADHS #PTBS #Appentwicklung #NichtKönnenToleranz #NUKA
#PromptEngineering #programming
nuka.ainuka | Resonanzbasierte Artificial Intelligence
Replied in thread
So I code with ChatGpt/Claude.
First, it's not like ordinary coding.
If you expect to vibe code, you are going to have a very bad time.
Second. The more definitions you give the #AI, the better.
Give parameters what you want to expect.
Third, spec it. Give as much specifications as you can. You want that text window to scroll?
Propose an array or a list structure.
Leave as little to imagination as possible, the thing has very little of it and it will try to please you hard, it will make shit up.
Fourth. Give overall instructions. I usually say something along the lines of "Do not code unless clear instructions are given". Else the thing will launch into code at the first prompt.
Fifth, I used to get it to Pseudocode. Now I just usually say "Restate the problem". Just to make sure the machine understands what it's doing.
Checkpoint. When you have code that works, designated it as "Version X.1" because inevitably the machine will fuck it, esp if you're introducing a notable change.
Seventh, learn #promptengineering, most people have NFI how to use the #LLM esp. if they are naturally hostile towards the tech.
E.g. If I really want the model to pay attention, I will say something like: DIRECTIVE: Blah blah.
Lastly, this should go without saying, the free models suck, pay the broligarch tax for the smarter engine.
It helps if you understand a little how LLMs work, today for example I gave a prompt to just keep latest checkpoint and specs and flush everything else from the session context as it tied itself into knots
There are other tips.
P.S. If this is not your sport, just mute and move on, don't be rude
Excited to share our (@janispagel, @nilsreiter) latest work at LaTeCH-CLfL 2025:
Prompt Engineering in Computational Literary Studies – Promise vs. Practice
We test how reliably LLMs generate sequence labels in a CLS context:
same prompts, different splits prompt rewording
performance-boosting phrases
Findings: results vary by split & wording; fixed phrases rarely help.
ACL AnthologyEvaluating LLM-Prompting for Sequence Labeling Tasks in Computational Literary StudiesAxel Pichler, Janis Pagel, Nils Reiter. Proceedings of the 9th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature (LaTeCH-CLfL 2025). 2025.
Do you want to Master Prompt Engineering? Here’s my overview on how to Prompt like a Pro!
#promptEngineering #ConversationalAI #GenerativeAI #AIPrompts #PromptDesign #ZeroShot #FewShot #ChainOfThought #AIForBusiness #AIEdge #AIProductivity #WorkSmarter #DigitalTransformation #TechLeadership #FutureOfWork #Innovation #LinkedInCreators #AIInsights #TechTips #CareerGrowth
www.linkedin.comPrompt Like a Pro: How to Master the Language of AIWelcome to the world of AI, where just like in real life, your words are the magic wand. Prompt engineering is no longer a secret art known only to a few AI sorcerers.
Guten Morgen!
Erstmal danke ich euch für all die lieben Worte – sie bedeuten mir unglaublich viel.
Es ist das erste Mal, dass ich diesen Screenshot jemandem außerhalb von Familie und Freundeskreis gezeigt habe.
Hier habe ich noch eine kleine Testfrage aus dem Modul „Beziehung“ für euch.
Sie zeigt ganz gut, warum mein System anders funktioniert als viele andere.
#Selbstfürsorge #ADHS #PTBS #Alltagskämpfe #Appentwicklung #Neurodivergenz
#appentwicklung #ki #ai #PromptEngineering
#appdevelopment
