Ellis Pratt (@ellispratt) header
Ellis Pratt (@ellispratt) profile picture

Director @ Cherryleaf. Technical writing services for lower customer churn #techcomm . These days at the place where the sky is blue.

London
Joined April 2008
Twitter is not The Marketplace of Ideas, but a Three Card Monty with you as the rube. The House always wins.
1
84
Just mass deleted 40231 tweets from Twitter with @redactdev redact.dev
1
117
Feeling like Caesar at the Great Library of Alexander...
2
79
If we were to offer a live (via Teams) one day course in using AI in technical communications, what would you like it to cover?
1
1
117
Ellis Pratt retweeted
"Hey Claude with computer use, watch this construction site video & write up things you see that dangerous or good, create a spreadsheet of critical issues to address" (sped up) How firms use AI as manager, coach or panopticon is going to have a big impact on what work becomes.
110
617
118
5,591
832,055
Ellis Pratt retweeted
I am genuinely impressed Google has quietly released “Learn about” a genius new AI tool: You can enter any topic you want to learn and you'll be able to dive right in VERY easily. It suggests the related aspects, simplifies, illustrates, etc. More below:
71
330
70
2,578
329,728
More AI chatbot experimenting yesterday. You can point it at a Github/Lab documentation repository and get it to produce decent release notes about said documentation.
57
I was noodling around with ChatGPT on Friday, and discovered it can generate some nice reports and summaries of issues from a Github or GitLab repository. Handy for project management and project reviews. For example: categorising what the docs team has been spending its time on.
1
79
Ellis Pratt retweeted
'I never thought leopards would eat MY face,' sobs woman who voted for the Leopards Eating People's Faces Party.
808
57,990
7,666
194,893
Guess the crime
Replying to @BGatesIsaPyscho
We are going to stop this crime.
146
744
12
20,614
1,755,831
Must be a Cowasaki 🐮
74
129
27
652
58,843
Ellis Pratt retweeted
Six months in and we’re bringing you the best Bard yet: Bard now: - integrates with your personal apps & services - is the only language model to actively admit how confident it is in its response - admits when it made a mistake - expanded image input to 40+ languages - is powered by the most capable model to date BARD EXTENSIONS We’re taking our most capable model version and allowing you to collaborate with your Google apps & services like Gmail, Docs, Drive, Maps, and more. IMPORTANT: When you opt in to use personal information like Gmail with Bard, we never train the model on your private data or expose human reviewers to it. More in Bard’s Help Center. CHECKING CONFIDENCE Bard is also the first language model to actively admit how confident it is in it’s response: using the updated Google It button, you can now see confident claims in green along with a link and lower certainty and even (GASP) when it makes a mistake in orange. These capabilities are coming worldwide in English to start. We’ll bring more languages and partners soon. EXPANDING TO MORE LANGUAGES On top of this, images in prompts and responses are now live in over 40 languages. We also have richer sharing to allow you to build on prompt ideas with your friends & colleagues. We can’t wait to see what happens when you use Bard to bring your curiosity and your ideas to life. Check it out: bard.google.com
129
281
74
1,753
637,745