t0ha (@t0ha@mastodon.social)
Prompt Engineer: Beyond the Buzzword
Can you really work as a prompt engineer? Let's find out the opinion of an expert and some essential skills and tools. In the bustling world of tech, the emergence of “prompt engineer” as a professional title has sparked a mix of curiosity and skepticism.
Tags: #ai, #llm, #promptengineering
via Pocket https://ift.tt/cYF1H5u
May 02, 2024 at 02:53PM
Show Original Post
infosec_jcp (@infosec_jcp@infosec.exchange)
#PromptEngineering 🤖♻️🔥
#NextSlide #TedTalk #♻️🔥
Show Original Post
simondueckert (@simondueckert@colearn.social)
So langsam geht es in den Countdown, in 8 Tagen startet der #kimooc24: https://youtu.be/EOoB-WDLp9U
Da lernt ihr alles zu #KünstlicheIntelligenz & #Wissensarbeit #GenAI #ChatGPT #Copilot #RAG #Prompting #PromptEngineering uvm.
Show Original Post
chrisvitalos (@chrisvitalos@sigmoid.social)
🚀 Are you creating #GenAI applications with #LLM? Are you experiencing #hallucinations? I overcame such a challenge by using #PromptEngineering. Dive into my latest blog post, "Making #AI Less of a Hallucination", where I outline how I tackled this issue to make a GenAI application more reliable 💡✨
#GenerativeAI #ArtificialIntelligence #MachineLearning
#hallucination
https://blog.vitalos.us/2024/04/making-ai-less-of-hallucination.html
Show Original Post
poing (@poing@phpc.social)
Just as in a game of darts, where even an expert player can make wild shots despite their high level of skill and precision, the accuracy of large language models (#LLMs) reflect this reality. Regardless of #PromptEngineering skills, achieving flawless outputs remains akin to aiming for a perfect game; elusive, yet continuously pursued. Just as no player can consistently hit a perfect shot, complete accuracy in #LLM outputs will always be an unattainable goal. #AI
Show Original Post
tero (@tero@rukii.net)
Did you know that your prompts are a valuable knowledge asset?
Prompt engineering is not really about hacks and tricks, but is mostly about writing down #AI accessible documentation about the domain, the processes and the tasks inside the processes.
Typically this creates the following types of valuable and transferrable knowledge assets:
- Silent knowledge about the domain, the processes and the tasks now written down.
- Stored task performances along with instructions for the tasks, which you can refine and curate to fine-tune or continually train any AI models to become better at performing these kinds of tasks.
- Stored performances of task evaluations which again you can refine, curate and use to continually train any AI model to become better at task evaluations.
- AI searchable knowledge assets, for example #RAG databases.
- AI enabled APIs and tools relevant for the domain, so that any AI system is able to integrate to the systems relevant to the domain, and also use external tools necessary for performing meaningful work in the domain.
- Chosen and curated knowledge sources for the domain, such as text books and course materials acquired from external sources.
Many companies are understanding #PromptEngineering and related data and evaluation pipelines and assets incorrectly, and so the organization doesn't support the true mission of this work.
Give your prompt engineers access to the domain experts, and empower them to build holistic domain integrations and self-refining processes around these types of valuable and transferrable knowledge assets so that they will support both AI accessibility to the domain and recursive self-improvement.
Show Original Post
bobchao (@bobchao@floss.social)
After conducting several rounds of tests, I began to question the effectiveness of #AutoPrompt in solving real-world issues. In my experience, the end results were worse than those obtained from #gpt-prompt-engineer, and the cost was over 10 times higher.
I'll keep trying but perhaps I lack the understanding of how to use AutoPrompt effectively. :/
Show Original Post
bobchao (@bobchao@floss.social)
https://arxiv.org/abs/2402.03099
"The generation setting is composed of two parts: generating the ranker prompt and then using the ranker to optimize the generation task prompt"
We human are so good at using tools to improve our workflow, isn't it?
#AutoPrompt #ai #gpt #PromptEngineering
Show Original Post
salcode (@salcode@phpc.social)
I was recently working with a #LLM, which led to me modifying this classic quote. 😀
Show Original Post
bobchao (@bobchao@floss.social)
https://gamma.app/docs/Prompt--hjhqmaqlpqtcfxo?mode=doc #promptengineering 感恩 ihower 整理資料
Show Original Post
remixtures (@remixtures@tldr.nettime.org)
#AI #GenerativeAI #LLMs #PromptEngineering #TechnicalWriting #SoftwareDocumentation #Productivity: "Many tech writers have a constant fear that AI will take our jobs. I often think, what I’m doing isn’t rocket science. Any person with some education can do it. And yet, just as engineers struggle to write, tech writers frequently struggle with AI tools. They don’t understand how to use them effectively. Even though “prompt engineering” is often a ridiculed term online, again and again I hear feedback from TWs about AI not being useful to them, or they simply don’t have interest in AI, as if it’s irrelevant to their work. This blows me away. When I can ramp up on a product in an hour and write a user guide in a couple of days, and code a doc publishing script that automates even more tasks, how can AI not be useful? How can it not be essential?
An often repeated saying is that AI tools won’t replace us, we’ll be replaced by those who know how to use AI tools. I feel like this is more and more true. Consider this scenario: You hire a roofer to install a new roof, which mainly involves removing the old shingles and installing new ones. One roofer arrives with a hammer. It will take this roofer 2 weeks to do the job. Another roofer arrives with a pneumatic roofing nailer power tool. It will take this roofer 3 days to do the job. The cost of the first roofer is 4 times that of the second. The output is pretty much the same. Which roofer do you hire?
It’s the same with tech writers. Suppose you have a large project. One tech writer can create the documentation using AI tools in a quarter of the time, while the other will take 75% longer. Which tech writer do you hire?
Fortunately, I think tech writers can learn how to use AI tools as power tools. Especially with more awareness and knowledge about effective prompting techniques, tech writers can become much more productive using AI." https://idratherbewriting.com/blog/ai-is-accelerating-me
Show Original Post
MrBerard (@MrBerard@pilote.me)
I saw a legit online article the other day on 'prompt engineering 'for humans interlocutors. Detailing basic conversation skills, but with a literally dehumanising spin.
[Pr Farnsworth: "I don't want to live on this planet anymore"
Show Original Post