We're halfway through the first month of the year, which means that many of us are already on our way to breaking our New Year's resolutions.

The big picture: You can use ChatGPT, Gemini, Claude, Perplexity and other generative AI tools to help you keep those promises you made to yourself at least a little bit longer.

Why it matters: In the near term, at least, you're probably less likely to lose your job to AI than to lose it to someone who understands how to use AI, so you might as well experiment with it.

• If you diligently set resolutions to do more of something, you can use ChatGPT to track and remind you to do those things.
• You can ask Google Gemini to create events in your Google Calendar to block off time for your resolutions.
• If you want to do less of something and feel tempted to do it anyway, you can message or use voice chat with any of the big bots for support.
• OpenAI will even let you video chat (sort of) or call ChatGPT for support.

Between the lines: Many psychologists and productivity experts suggest that an effective way to keep resolutions is to make them "SMART": specific, measurable, achievable, relevant and time-bound.

I tried this prompt: "I would like to eat better. Turn this into a SMART goal," and ChatGPT responded:

To turn "I would like to eat better" into a SMART goal (Specific, Measurable, Achievable, Relevant, Time-bound), here's a suggestion:

SMART Goal: "I will eat at least five servings of fruits and vegetables per day and replace sugary snacks with healthier options (like nuts or yogurt) at least five days a week for the next three months to improve my overall diet and well-being."

Breakdown:

• Specific: Focuses on fruits, vegetables, and reducing sugary snacks.
• Measurable: Five servings and five days per week are clear targets.
• Achievable: Practical changes rather than an extreme diet.
• Relevant: Tied to your desire to eat better and improve health.
• Time-bound: A three-month timeline sets a clear endpoint for evaluation.

One of the biggest differences between searching the web and prompting a chatbot is that you can have a conversation with the chatbot.

• I prompted ChatGPT to give me a weekly meal plan to help me achieve this goal. I added that I was a pescatarian.
• The pescatarian meal plan it gave me was good, but one recipe contained lentils, and I am not a fan. So I asked for another recipe.
• It offered a replacement and updated its memory so it will (I hope) never suggest another lentil again.

Zoom in: Chatbots are like endlessly patient, eager-to-please personal assistants.

• Once you have a meal plan you can ask most chatbots to alter it for more protein, less fat, more affordable ingredients, and so on.
• Then you can ask the chatbot to give you a grocery list and it will even tell you which aisle to find each item.
• Then you can ask it for 10 or 1,000 different meal plans. The chatbot will not get overwhelmed (but you might).

Zoom out: You can use similar prompts to help you exercise more, drink less alcohol, drink more water, spend less time mindlessly scrolling, read more books, or do more or less of just about anything you've resolved to do more or less of.

Most chatbots speak multiple languages so they're ideal if your resolution is to learn a new one.

A spokesperson for OpenAI suggested this prompt: "I want to learn [specific skill or language], and I'd like you to act as my personal coach. Please help me create a structured learning plan with weekly goals and daily exercises tailored to a beginner level. Include explanations, examples, and practice activities for each step. "

• If you're having trouble keeping this goal use this prompt: "Provide tips for staying motivated and recommend external resources or tools that complement your guidance. At the end of each week, assess my progress and adjust the plan as needed. Let's start with an overview of [the skill or language] and the first week's plan."

A spokesperson for Anthropic offered this set of prompts for keeping language learning goals: "Hi Claude! I want to learn Spanish this year. I can practice for about 30 minutes each day, usually in the evenings. I'm a complete beginner and my goal is to order food in Spanish when I visit Mexico next year. Can you help me make a learning plan?"

• You can also ask Claude to create simple practice dialogues for real situations, 15-minute daily exercises, ways to practice while doing everyday tasks and creative ways to keep at it.

Yes, but: If your resolutions involve spending less time immersed in your digital devices, using AI to keep you on goal could be tricky.

• Also, generative AI is a notorious energy hog, and all of our prompts have a significant impact on the environment.
• You may want to check your chatbot-of-choice's privacy policy and practices.

The vast majority of Americans use products that involve AI, but their views of the technology remain overwhelmingly negative, according to a Gallup-Telescope survey published yesterday.

Why it matters: The rapid advancement of generative AI threatens to have far-reaching consequences for Americans' everyday lives, including reshaping the job market, impacting elections, and affecting the health care industry.

The big picture: An estimated 99% of Americans used at least one AI-enabled product in the past week, but nearly two-thirds didn't realize they were doing so, according to the poll's findings.

• These products included navigation apps, personal virtual assistants, weather forecasting apps, streaming services, shopping websites and social media platforms.
• Ellyn Maese, a senior research consultant at Gallup, told Axios that the disconnect is because there is "a lot of confusion when it comes to what is just a computer program versus what is truly AI and intelligent."

Zoom in: Despite its prevalent use, Americans' views of AI remain overwhelmingly bleak, the survey found.

• 72% of those surveyed had a "somewhat" or "very" negative opinion of how AI would impact the spread of false information, while 64% said the same about how it affects social connections.
• The only area where a majority of Americans (61%) had a positive view of AI's impact was regarding how it might help medical diagnosis and treatment.

What they're saying: Given the attention paid to deepfakes in recent months, surveyors expected to see negative results in areas surrounding misinformation, but they didn't foresee just how gloomy the picture would be.

• "We were actually surprised by how negative perceptions actually were in a lot of these areas," like national security, Maese told Axios.
• But opinions likely won't result in much less usage of these AI-enabled products, she noted.
• "I don't see anybody signing off of social media or streaming apps anytime soon, whether they know that it uses AI or not," she said.

State of play: The survey found that 68% of Americans believe the government and businesses equally bear responsibility for addressing the spread of false information related to AI.

• 63% said the same about personal data privacy violations.
• Majorities of those surveyed felt the same about combatting the unauthorized use of individuals' likenesses (62%) and AI's impact on job losses (52%).
• In fact, the only area where Americans felt differently was when it came to national security threats; 62% of those surveyed said the government bore primary responsibility for reducing such threats.

• President Biden will sign a new executive order covering software security and AI-powered defense. (Axios)

Tesla's Vision system clearly needs a little more "training." Pun intended.