/ / THEFUTURE /
In this issue: When ChatGPT fails at basic geography, who’s really holding it wrong? The Wall Street Journal’s Tess Jeffers on lightweight AI experiments and changing audience expectations. Plus: When AI tools promise to fix your prompts.
What we’re talking about: Is the new ChatGPT smarter now? Over the past few days, there have been examples that seemingly prove the opposite. People have asked it to create maps of Europe or Germany with poor results. Someone wanted to know exactly when Cisco introduced the C1101-4P router.
On one hand: yeah, really dumb. On the other hand: that’s just not how this works.
This reminds me of the iPhone 4. Fifteen years ago, Apple released an iPhone that didn’t play particularly well with human hands – reception got worse when you gripped it and unknowingly blocked the antenna in the bottom left corner. Apple’s response back then was basically: You’re holding it wrong.
When you spend some time with large language models, you eventually learn: this is lossy compression. With emphasis on: lossy. A Blurry JPEG of the Web. Details get blurred, and it’s almost an art to hit the sweet spot – where are the details still sharp and accurate, where do the models start to hallucinate?
And it’s pretty brazen, of course, that platforms put up chatbots and say: universal tools, mega-smart. And then largely leave users on their own, and when they rely on the output, it’s like: well, you didn’t read the fine print, and the AI fanboys laugh at you.
(When you tell GPT-5 not to paint a picture but to create code, it can be just as disappointing.)
What else I’ve been reading:
Low-investment, high-stakes: While newsrooms scramble to keep up with AI, Tess Jeffers is taking a different approach at The Wall Street Journal. Her take: lightweight experiments that prepare for a future where audiences need something different from journalism.
Three Questions with Tess Jeffers
Tess Jeffers is the Director of Newsroom Data and AI at The Wall Street Journal.
Three Questions with Tess Jeffers
Tess Jeffers is the Director of Newsroom Data and AI at The Wall Street Journal.
What's on your mind lately?
I keep coming back to Ezra Eeman’s LinkedIn post from a few months ago, where he laid out the unique value proposition that journalism offers—value that AI can’t replicate.
This framework has been a useful guide in our newsroom as we think about how our journalism needs to evolve in a genAI world. It’s also shaped our conversations with tech and product teams about what not to build—since some audience needs can already be met faster, better, and more seamlessly by AI.
What do you wish you had known a year ago?
Around this time last year, my role expanded from editorial data science & analytics to also leading newsroom’s AI initiatives. I wish I had known just how much this role would feel like changing the engine while flying the plane.
We’ve spent a lot of the time working with our tech and product teams to find ways to experiment with AI in lightweight, low-investment ways. They need to keep the business running and deliver on day-to-day priorities, while also carving out space to test, learn, and explore what we should be building for the next 3-5 years.
Audience expectations are already starting to change, and we need to learn about those quickly and start building for the future where audiences need more direct, community oriented and trusted journalism.
What's a good/funny/great website?
Not a website and still media – but I’m a big fan of this print-first publication called County Highway. They have a site, but the real experience is the massive, beautifully designed broadsheet newspaper. It feels like such a luxury to disconnect, slow down and deeply engage.
Previously: Nieman Lab’s Andrew Deck, INMA’s Sonali Verma, Newsroom Robots’ Nikita Roy, and Republik’s David Bauer.
Hands on: Role, task, context, example – that’s how you write a good prompt. In workshops these days, I like to tell people: just ask the AI itself what would make the prompt better. And on top of that: OpenAI and Anthropic offer specialized tools for optimization.
Just a quick little example. Before:
You are an experienced editor. Read the following text carefully: What is the single most impactful change that would significantly improve this text's clarity, engagement, or usefulness for its intended audience?With OpenAI Prompt Optimizer for GPT-5:
# Role and Objective
- You are an experienced editor tasked with evaluating and enhancing written content.
# Instructions
- Carefully read the provided text.
- Begin with a concise checklist (3-7 bullets) of your evaluation steps; keep items at a conceptual level, not implementation details.
- Identify the single most impactful change that would significantly improve the text's clarity, engagement, or usefulness for its intended audience.
- Clearly describe this change and explain its expected impact.
# Output Format
- Return only your recommendation, formatted as a brief summary statement.
# Verbosity
- Keep responses concise and focused on actionable editorial improvements.
# Stop Conditions
- Complete the task once you have suggested and explained the single most impactful change.With Anthropic Console for all recent Claude models:
You are an experienced editor tasked with improving a piece of text. Your goal is to identify the single most impactful change that would significantly improve the text's clarity, engagement, or usefulness for its intended audience.
Here is the text you need to analyze:
<text_to_analyze>
{{TEXT}}
</text_to_analyze>
Please follow these steps:
1. Carefully read and analyze the provided text.
2. Consider various aspects of the text, including but not limited to:
- Clarity of ideas and language
- Engagement factor for the intended audience
- Overall usefulness of the information presented
- Structure and organization
- Tone and style
3. Identify the single most impactful change that would significantly improve the text. This change should have the greatest positive effect on the text's clarity, engagement, or usefulness for its intended audience.
4. Before providing your final answer, use the <scratchpad> tags to think through your reasoning. Consider multiple potential changes and why you believe your chosen change would be the most impactful.
5. In your final response, include:
a) A justification for why you believe this change would be the most impactful. Explain how it would improve the text's clarity, engagement, or usefulness.
b) The specific change you are recommending.
6. Format your response as follows:
<answer>
<justification>
[Your justification here]
</justification>
<recommended_change>
[Your specific recommended change here]
</recommended_change>
</answer>
Remember, you are looking for the single most impactful change. Focus on the change that would bring about the most significant improvement to the text.Now, does it work better? It’s definitely an example of how AI doesn’t just automatically know what to do when you ask. Clear instructions matter. In one case, Claude suggested that instead of writing an article, I should write a structured checklist. Do I want to hear that right now? Well.
This is THEFUTURE.
