In the coming months Copilot for Microsoft 365, the paid service that adds an AI assistant to Office apps, will be updated with a new auto-complete feature that offers suggestions to improve AI prompts.
Don’t wait to get comfortable with AI. Try out a few of these prompts and flex your chatbot muscles. You’ll see just how easy they are to use.
A great resource with examples of effective prompts, from Claude provider Anthropic.
The company last week unveiled a new blog series with tips, tricks, and suggestions on how you can get the most out of Gemini for Google Workspace. You can apply the advice to almost any AI chatbot.
Bad actors attempt to bypass safeguards with the intent to achieve unauthorized actions, which may result in what is known as a “jailbreak.” The consequences can range from the unapproved but less harmful to the very serious.
“I’ve pulled together a series of fun prompts to try with ChatGPT that work with free & paid versions & covered a range of topics with these prompts, as well as different prompting styles including one where you need to enter a multi-prompt conversation.”
This technique embeds a hidden instruction within the essay prompt that directs the inclusion of specific, unrelated words in the student’s submission. Formatted in white text and minimised in size, it remains unseen by students but is detected by the AI.
There’s a character limit for user entries in Edge, but that looks like it might change thanks to an upcoming ‘Notebook’ option. Windows Latest reports that this feature will expand the character limit for prompts to 18,000 characters.
In a recent release update for Gemini AI, Google has implemented an efficient way to alter bits of the generated replies.
It formats user-entered requests—typically known as prompts—into standard statements or sentences as normal with one exception: a single word, known as a mask, is represented by ASCII art rather than the letters that spell it.
A helpful list of prompts.
New research suggests that prompt engineering is best done by the model itself, and not by a human engineer.
When selecting (by highlighting) a part of Gemini’s response to your prompt, a pencil/sparkle icon appears to “Modify selected text.” This opens a box with Regenerate, Shorter, Longer, and Remove options, as well as an open text field.
“I have a strong hunch that tipping does in fact work to improve the output quality of LLMs and its conformance to constraints, but it’s very hard to prove objectively…”
“A programming question is fed to the underlying large language model, and it’s asked to describe and summarize the problem. That information then guides how it should begin to solve the problem…”
“As powerful as Bard is, it can’t read your mind (at least, not yet), so you need to feed it the right questions and prompts to get it to behave how you want it to…”
“Kaspersky’s research includes a screenshot of a post advertising software for malware operators that uses AI to not only analyze and process information, but also to protect the criminals by automatically switching cover domains…”
“I operate a business in [describe your business and niche]. To gain mastery and establish myself as an expert, I’m looking for potentially overlooked strategies that could propel me ahead in my field…”
Nonsense words can trick popular text-to-image generative AIs such as DALL-E 2 and Midjourney into producing pornographic, violent, and other questionable images. A new algorithm generates these commands to skirt these AIs’ safety filters.
Why does this matter? First, different conversation types serve distinct information needs and demand varied UI designs. Second, there is no one optimal conversation length — both short and long conversations can be helpful, as they might support different user goals.
To create an academia-worthy structure, Bilal says it is fundamental to master incremental prompting, a technique traditionally used in behavioural therapy and special education. It involves breaking down complex tasks into smaller, more manageable steps.
The study revealed that large language models may, in fact, be able to understand and respond to emotional cues.Researchers found that LLMs produced higher-quality outputs when emotional language was used to talk to AI chatbots.
On Saturday, X-user Denis Shiryaev devised a visual jailbreak that circumvents Bing Chat’s CAPTCHA filter by tricking it into reading the inscription on his imaginary deceased grandmother’s locket.
Should you be typing that information into an AI chatbot? Do you know where that information is going, how it might be used, and how many people might see it? In this brief guide – adapted from my new book Getting Started with ChatGPT and AI Chatbots – we look at the questions we need to ask before we hit Enter. This is highly recommended for anyone who uses an AI chatbot – either for work or in personal pursuits.
n this latest study, DeepMind researchers found “Take a deep breath and work on this problem step by step” to be the most effective prompt when used with Google’s PaLM 2 language model. The phrase achieved the top accuracy score of 80.2 percent in tests against GSM8K, which is a data set of grade-school math word problems.
In a new paper, researchers from DeepMind propose a new way: Optimization by PROmpting (OPRO), a method that uses AI large language models (LLM) as optimizers. The unique aspect of this approach is that the optimization task is defined in natural language rather than through formal mathematical definitions.
Prompt injection attacks fall into two categories—direct and indirect. And it’s the latter that’s causing most concern amongst security experts. When using a LLM, people ask questions or provide instructions in prompts that the system then answers
Windows Copilot News 