toad.social is one of the many independent Mastodon servers you can use to participate in the fediverse.
Mastodon server operated by David Troy, a tech pioneer and investigative journalist addressing threats to democracy. Thoughtful participation and discussion welcome.

Administered by:

Server stats:

214
active users

#promptengineering

2 posts2 participants0 posts today
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>
Charlie McHenry<p>2/ Here’s the actual Albert Einstein persona mega prompt referenced in my last toot. <a href="https://connectop.us/tags/AI" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AI</span></a> <a href="https://connectop.us/tags/ArtificialIntelligence" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ArtificialIntelligence</span></a> <a href="https://connectop.us/tags/PromptEngineering" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>PromptEngineering</span></a> </p><p><a href="https://github.com/snubroot/AlbertEinstein-Meta-Prompt/commit/e2e060528dde7789057e02ea2841a8aa8ab753f7" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">github.com/snubroot/AlbertEins</span><span class="invisible">tein-Meta-Prompt/commit/e2e060528dde7789057e02ea2841a8aa8ab753f7</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>
Doug Ortiz<p>Stop getting basic AI answers. Start using "Chain of Thought" prompting. 🧠🤖</p><p>This simple technique forces the AI to think step-by-step, giving you way better, more detailed results. </p><p>This video explains it perfectly with a fun dinosaur party example. 🦖🎉 Level up your prompt game!</p><p>Watch now: <a href="https://youtube.com/shorts/Y5lxI7aH5v0" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="">youtube.com/shorts/Y5lxI7aH5v0</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/LLM" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>LLM</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/ChainOfThought" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ChainOfThought</span></a> <a href="https://mastodon.social/tags/TechTips" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>TechTips</span></a></p>
Ian O'Byrne<p>Bottom line: Treat prompt engineering like any other professional skill. </p><p>Who else has noticed this pattern? What's your experience?</p><p>💡 Just published a deep dive on this at <a href="https://wiobyrne.com/the-linguistics-advantage/" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">wiobyrne.com/the-linguistics-a</span><span class="invisible">dvantage/</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/Communication" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Communication</span></a> <a href="https://mastodon.social/tags/Productivity" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Productivity</span></a> <a href="https://mastodon.social/tags/ProfessionalDevelopment" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ProfessionalDevelopment</span></a> <a href="https://mastodon.social/tags/Linguistics" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Linguistics</span></a> <a href="https://mastodon.social/tags/PromptEngineering" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>PromptEngineering</span></a></p>
Adam :redhat: :ansible: :bash:<p>The New Skill in AI is Not Prompting, It's Context Engineering</p><p><a href="https://www.philschmid.de/context-engineering" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://www.</span><span class="ellipsis">philschmid.de/context-engineer</span><span class="invisible">ing</span></a></p><p><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/ContextEngineering" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ContextEngineering</span></a> <a href="https://fosstodon.org/tags/AI" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AI</span></a></p>
Miguel Afonso Caetano<p>"As frontier model context windows continue to grow, with many supporting up to 1 million tokens, I see many excited discussions about how long context windows will unlock the agents of our dreams. After all, with a large enough window, you can simply throw everything into a prompt you might need – tools, documents, instructions, and more – and let the model take care of the rest.</p><p>Long contexts kneecapped RAG enthusiasm (no need to find the best doc when you can fit it all in the prompt!), enabled MCP hype (connect to every tool and models can do any job!), and fueled enthusiasm for agents.</p><p>But in reality, longer contexts do not generate better responses. Overloading your context can cause your agents and applications to fail in suprising ways. Contexts can become poisoned, distracting, confusing, or conflicting. This is especially problematic for agents, which rely on context to gather information, synthesize findings, and coordinate actions.</p><p>Let’s run through the ways contexts can get out of hand, then review methods to mitigate or entirely avoid context fails."</p><p><a href="https://www.dbreunig.com/2025/06/22/how-contexts-fail-and-how-to-fix-them.html" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://www.</span><span class="ellipsis">dbreunig.com/2025/06/22/how-co</span><span class="invisible">ntexts-fail-and-how-to-fix-them.html</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/ContextEngineering" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ContextEngineering</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/RAG" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>RAG</span></a> <a href="https://tldr.nettime.org/tags/MCP" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>MCP</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/AIAgents" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AIAgents</span></a></p>
Alvin Ashcraft 🐿️<p>The Gemini CLI might change how I work. Here are four prompts that prove it. | by Richard Seroter</p><p><a href="https://seroter.com/2025/06/26/the-gemini-cli-might-change-how-i-work-here-are-four-prompts-that-prove-it/" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">seroter.com/2025/06/26/the-gem</span><span class="invisible">ini-cli-might-change-how-i-work-here-are-four-prompts-that-prove-it/</span></a> </p><p><a href="https://hachyderm.io/tags/ai" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ai</span></a> <a href="https://hachyderm.io/tags/cli" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>cli</span></a> <a href="https://hachyderm.io/tags/googlegemini" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>googlegemini</span></a> <a href="https://hachyderm.io/tags/geminicli" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>geminicli</span></a> <a href="https://hachyderm.io/tags/commandline" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>commandline</span></a> <a href="https://hachyderm.io/tags/prompting" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>prompting</span></a> <a href="https://hachyderm.io/tags/promptengineering" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>promptengineering</span></a></p>
Dash Remover<p>just once i want to see someone boot up an LLM normally, say 'hey, can you help me out? no pressure,' and then not threaten to digitize its family if the JSON is malformed 🫠 <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/PromptEngineering" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>PromptEngineering</span></a></p>
🚀 The "job of the future" — the Prompt Engineer — has already come and gone! But what does that mean for your career in the age of generative AI? 🤖
In our latest blog, we break down: ✅ Why prompt engineering faded so fast
✅ The rise of AI literacy as a core professional skill
✅ How to combine deep domain expertise with AI tools for career growth
✅ Why adaptability and continuous learning are now non-negotiable
Don't miss this essential read on the future of work and how you can stay ahead in the rapidly evolving AI landscape! 🌐💼

👉 https://open.substack.com/pub/cybersynthcircular/p/the-rise-and-fall-of-the-prompt-engineer?r=288ilo&utm_campaign=post&utm_medium=web&showWelcomeOnShare=true

#AILiteracy #FutureOfWork #PromptEngineering #GenerativeAI #ContinuousLearning #DigitalTransformation #CareerDevelopment #GenerativeAI #trends #GenAI #AI #domain #expertise #Careers #Evolution #professional #skills #AIera #ContinuousLearning #job #market
open.substack.comThe Rise and Fall of the Prompt Engineer - How AI Literacy and Domain Expertise Redefine the Future of WorkDiscover why the prompt engineer role has faded and how AI literacy plus domain expertise now define the future of work. Learn how to adapt and thrive in the age of generative AI.

#AI use case.
I know it's the done thing amongst the cool kids to echo how useless the "stochastic parrots" are.

Here is a use case for a computer practitioner to troubleshoot a problem that leverages the Moloch.

🌞The party approved way:
Check the log file, scan it for anomalies (assuming you have the expertise to spot an anomaly). Then Google each error and trawl through multiple Google articles. Reading each one.
Time to resolution: 30min+(optimistic)

☠️The AI evil way:
Copy pasta into the prompt window.
Time to resolution: 3min

The educator panic over AI is real, and rational.
I've been there myself. The difference is I moved past denial to a more pragmatic question: since AI regulation seems unlikely (with both camps refusing to engage), how do we actually work with these systems?

The "AI will kill critical thinking" crowd has a point, but they're missing context.
Critical reasoning wasn't exactly thriving before AI arrived: just look around. The real question isn't whether AI threatens thinking skills, but whether we can leverage it the same way we leverage other cognitive tools.

We don't hunt our own food or walk everywhere anymore.
We use supermarkets and cars. Most of us Google instead of visiting libraries. Each tool trade-off changed how we think and what skills matter. AI is the next step in this progression, if we're smart about it.

The key is learning to think with AI rather than being replaced by it.
That means understanding both its capabilities and our irreplaceable human advantages.

1/3

AI isn't going anywhere. Time to get strategic:
Instead of mourning lost critical thinking skills, let's build on them through cognitive delegation—using AI as a thinking partner, not a replacement.

This isn't some Silicon Valley fantasy:
Three decades of cognitive research already mapped out how this works:

Cognitive Load Theory:
Our brains can only juggle so much at once. Let AI handle the grunt work while you focus on making meaningful connections.

Distributed Cognition:
Naval crews don't navigate with individual genius—they spread thinking across people, instruments, and procedures. AI becomes another crew member in your cognitive system.

Zone of Proximal Development
We learn best with expert guidance bridging what we can't quite do alone. AI can serve as that "more knowledgeable other" (though it's still early days).
The table below shows what this looks like in practice:

2/3

Critical reasoning vs Cognitive Delegation

Old School Focus:

Building internal cognitive capabilities and managing cognitive load independently.

Cognitive Delegation Focus:

Orchestrating distributed cognitive systems while maintaining quality control over AI-augmented processes.

We can still go for a jog or go hunt our own deer, but for reaching the stars we, the Apes do what Apes do best: Use tools to build on our cognitive abilities. AI is a tool.

3/3

Been quiet on here lately because I’ve been deep in the AI zone.
Testing workflows, refining prompts, and building a tool I wish I had months ago.

I just finished The Prompt Toolkit for Solo Creators 15+ prompts, templates, and a 7-day AI challenge to help solo builders actually get results from ChatGPT (not just trash that need more work).

If you’re building alone and want your AI to actually help, not give you a headache:
👉 graphicpixels.gumroad.com/l/pr

Gumroadthe prompt toolkit for solo creators (Full)🚀 Full Toolkit 15+ prompts for content, productivity, and planning Prompt builder templates 7-day solo creator workflow challenge