![\"Relaxed](\"https:\/\/i0.wp.com\/blogs.sussex.ac.uk\/librarycollections\/files\/2024\/01\/christin-hume-mfB1B1s4sMc-unsplash-1024x683.jpg?resize=485%2C324&ssl=1\" "\\"Using")
Words, word, words\u00a0<\/strong> ChatGPT, Claude and Perplexity <\/strong> At face value all three provide a similar output. All three generate eloquent responses in English and other world languages. <\/p>\n\n\n\n AI document tactics<\/strong> In 2023, though, lets walk though my approach.\u00a0 One of the AI bullet points reads<\/strong> Me<\/strong>: \u201cWhat does it say about innovation? No more than 20 words.\u201d <\/em> Me: \u201cReword this without jargon for a non-technical reader.\u201d Take-home message\u00a0<\/strong> Direct comparison of key features<\/strong> In the next post <\/strong> By Tim Graves ChatGPT, Claude and Perplexity I’ll be talking about free versions of three tools I’ve found most useful over the last year when it comes to handling long emails and documents. ChatGPT Claude Perplexity.ai AI document tactics To illustrate how…<\/span><\/p>\n
In subsequent blog posts I plan to talk about AI in data analysis\/visualisation, image generation, speech, and maybe even music and video.\u00a0 But for now, I want to focus on how AI has helped me deal with words.\u00a0The daily fusillade of emails, articles, reports, newsletters, web pages.\u00a0<\/p>\n\n\n\n
I’ll be talking about free versions of three tools I’ve found most useful over the last year when it comes to handling long emails and documents. <\/p>\n\n\n\n
To illustrate how AI has changed my tactics, let\u2019s imagine that someone (malevolent) asks me to read the blockbusting government publication: \u201cLevelling Up the United Kingdom: Executive Summary\u201d
My 2022 methodology would have involved gloom at the prospect of dragging my eyes from cover to cover. Maybe I would skim read a few bits, or perhaps I would add it to a queue of other \u2018long-and-important-but-boring\u2019 documents. <\/p>\n\n\n\n
I would copy and paste the contents into a ChatGPT session (or upload the file to Perplexity or Claude).\u00a0
I would then begin a dialogue with the text by typing in my questions:\u00a0
Me: \u201cWhat is the main point of this document, in 20 words?\u201d\u00a0
AI then provides me a one-liner that summarises the whole thing.\u00a0
I decide to find out a bit more.\u00a0
Me: \u201cIn 100 words of bullet points summarise the document.\u201d\u00a0
AI duly delivers me a list of the main points.\u00a0
Then,\u00a0
Me: \u201cWhat are the five key topics of the document?\u201d\u00a0
And,\u00a0
Me: \u201cWhat is the main conclusion in no more than 30 words?\u201d\u00a0
Immediately my relationship to the document has changed into a conversation.\u00a0#
I have a quick sense of what the text covers. Perhaps that is all I need in order to prioritise whether to read it straight away or put it aside.\u00a0
If I were to be hauled into a surprise meeting I would already be ahead of the game: able to fend off basic questions, and in a much happier position than everyone else who couldn\u2019t face even looking at it.\u00a0<\/p>\n\n\n\n
\u201cKey Focus: Boosting productivity, innovation, economic growth in less prosperous areas.\u201d
Let\u2019s suppose this sparks my interest, so I decide to probe further:<\/p>\n\n\n\n
So, already AI has summarised a long document for me, listed the key topics and allowed me to identify a thread I want to pursue.
Imagine this same approach applied to<\/strong>…
A long email,
A newsletter,
A product release notice,
A research paper,
The transcript of a meeting that I missed,
I get immediate insight without having to plough through every detail.<\/em>
I can go further and adapt the tone to suit my personal requirements:<\/p>\n\n\n\n
Me: \u201cExplain this to a 10-year-old.\u201d<\/em>
I can pull in information from outside the document, to clarify certain points:
Me: \u201cExplain what SME means.\u201d<\/em>
Perhaps English is not my first language, or the document is in a language unfamiliar to me?
Me: \u201cTranslate the document into Mandarin\/Welsh.\u201d<\/em>
Or I can get silly:
Me: \u201cRewrite the main points as a Shakespearean sonnet.\u201d
Me: \u201cWrite me a rap based on the primary conclusion.\u201d<\/em><\/p>\n<\/div><\/div>\n<\/div><\/div>\n<\/div><\/div>\n\n\n\n
The next time you face a long e-mail, document, or you need to catch up on meeting notes, I encourage you to experiment with one or more of the AI models.\u00a0You should be able to win back a few minutes or even hours of your day.\u00a0<\/p>\n\n\n\nChat GPT3.5 <\/td> https:\/\/chat.openai.com\/ <\/td><\/tr> Claude 2.1 <\/td> https:\/\/claude.ai\/ <\/td><\/tr> Perplexity.ai <\/td> https:\/\/www.perplexity.ai\/ <\/td><\/tr><\/tbody><\/table>
Each of the three tools has different strengths\/super-powers\/limitations: so, each might prove useful in different situations. The following table might help you decide which to try with any specific text. <\/p>\n\n\n\nModel <\/td> Message limit (approximate) <\/td> How long a document can it handle? <\/td> Can it search the Web? <\/td> Can I upload a file? <\/td><\/tr> Chat GPT 3.5 <\/td> 30 messages per hour <\/td> 10 pages <\/td> Only has knowledge from the Web up to January 2022. <\/td> No <\/td><\/tr> Claude 2.1 <\/td> 100 messages every 8 hours <\/td> 500 pages <\/td> No <\/td> Yes <\/td><\/tr> Perplexity.ai <\/td> 25 messages per day <\/td> 500 pages <\/td> Yes <\/td> Yes <\/td><\/tr><\/tbody><\/table><\/figure>\n\n\n\n
In my next blog post I will move on to how AI has saved me time and drudge with data analysis and visualisation. If you want to win back a chunk of your day from spreadsheets, join me next time. <\/p>\n","protected":false},"excerpt":{"rendered":"