Anthropic released a new version of Claude that accepts 100,000 tokens, or approximately 75,000 words of input.
This allows users to analyze and perform tasks on lengthy excerpts of books, code, documents, transcripts, and more.
Screenshot from Poe, June 2023Continue reading to learn more about the latest version of Anthropic AI chatbot, Claude-instant-100k, and see how it performs tasks compared to its competitors: ChatGPT, Bing AI, and Google Bard.
AI Chatbot Input Limitations
Want to ask questions about a piece of content? Here is the length of input you can submit to generative AI chatbots by OpenAI, Microsoft, and Google.
- OpenAI’s standard GPT-4 model offers 8,000 context tokens, whereas the extended context-length model offers 32,000 tokens / 25,000 words of input.
- The input box for the prompt on Bing AI chat shows 0/4000, suggesting it only accepts up to 4,000 characters. However, the chatbot accepted 40,400 characters of lorem ipsum and accurately counted that it was a total of 6,000 words.
- Google Bard accepts up to 10,000 characters.
Claude-instant-100k accepts – three times more input than the best GPT-4 model.
But how well can they follow directions?
I experimented with three tasks using Claude-instant-100k, ChatGPT Plus, Bing AI, and Google Bard. Here are the results.
Task #1: Edit An 1,580-Word List With Claude, ChatGPT, Bing, And Bard
The input: A list of 126 items (some of the first ChatGPT plugins) with 1,850 words / 12,500 characters.
The prompt: Can you rephrase and edit the descriptions for the following list:
[the list]
Claude Completed The Task
- Claude finished editing my list at item #126 with no hallucinations and followed the directions to rephrase the item descriptions.
- Compared to the other AI chatbots, Claude-instant-100k finished the task the fastest.
ChatGPT Default GPT-4 Hallucinated (Link To Chat)
- ChatGPT stops midway through item #37.
- I clicked Continue generating – ChatGPT finished #37 and stopped again.
- I prompted it to Please continue.
- ChatGPT begins listing items that were not in my original input.
- After a few more clicks to Continue generating, ChatGPT finished editing my list at item #142.
Bing AI Tried
- Bing accepted the entire prompt and list.
- It asked if this was what I was looking for – I told it yes and to please continue.
- After additional prompting it to please continue, Bing finished editing my list at item #126 without hallucinations.
- Unfortunately, it stopped rephrasing the descriptions after item #18 and output the list as I input it.
Bard Could Not Create Images
- Because of the 10,000-character input limitation, I could only submit 99 items from the list in the prompt.
- Bard responded, “I can’t create images yet so I’m not able to help you with that.” or “That’s not something I’m able to do yet.”
Ultimately, Claude-instant-100k completed the task with the most accuracy and speed.
You can compare the output from Claude, ChatGPT, and Bing to the original list of items in this Google Sheet.
Task #2: Summarize A 23,500-Word PDF With Claude, ChatGPT, Bing, And Bard
The input: 23,508 words / 125,104 characters copied from a PDF documenting TikTok’s responses to a hearing on how Congress can safeguard United States citizens from the social platform.
The prompt: Please summarize the following:
[the text]
Claude Succincinctly Summarized The Entire Text
Screenshot from Poe, June 2023ChatGPT Default GPT-4 Requested Something Shorter
Screenshot from ChatGPT, June 2023Bing AI Lost Its Connection
Screenshot from Bing, June 2023Bard Summarized The First 10,000 Characters
Screenshot from Google Bard, June 2023Task #3: Edit This PHP Code With Claude, ChatGPT, Bing, And Bard
The input: A PHP file with 14,787 characters.
The prompt: Can you debug the following:
[the code]
Claude Offered Some Suggestions
Screenshot from Poe, June 2023ChatGPT GPT-4 Code Interpreter Determined It Was Sound
Screenshot from ChatGPT, June 2023Bing AI Could Not Debug The Code
Screenshot from Bing, June 2023Bard Deemed The First 10k Characters Free Of Errors
Screenshot from Google Bard, June 2023Claude-instant-100k Outperforms Competitors
In just a few initial experiments with everyday tasks, it’s clear that the latest version of Claude from Anthropic can outperform its competitors.
Like ChatGPT, the experimental features for Claude are available for a price.
Poe subscribers can Claude-instant-100k on a desktop browser for $19.99 monthly, comparable to ChatGPT+ subscriber pricing.
Screenshot from Poe, June 2023If you have tasks that require lengthy input, give the new version of Claude a test drive.
Featured image: Koshiro K/Shutterstock
