or
or
or
Tags

Overview: Communications Tactics

Relevant resources

Visualising knowledge with MyHub.ai and ChatGPT (newsletter 2)
mathewlowry.myhub.ai
Card image

"If Charts lie, ChatGPT visualisations lie brilliantly". Exploring knowledge visualisations powered by ChatGPT, which can be particularly problematic because of the way the LLM's hallucinations - already hard to spot by their very nature - are also hidden behind the visualisation. But they have real potential as a creative muse.

ElevenLabs - Generative AI Text to Speech
elevenlabs.io

"text to speech and voice cloning software ... Create lifelike voiceovers for your content or use our AI voice generator as an easy-to-use text reader... spoken audio in any voice, style, and language ... renders human intonation and inflections "

04/11/2023
Duet AI in Google Workspace | Generative AI Tools for Work
workspace.google.com

Google's AI-powered assistant: "Duet AI is a powerful collaborator that can act as a coach, thought partner, source of inspiration, and productivity booster — all while ensuring every user and organization has control over their data... you must first have an eligible Google Workspace plan."Via this post on "creating the perfec…

Google Bard “Extensions” Are Here
generativeai.pub

"With Extensions, Bard can find and show you relevant information from the Google tools you use every day... across multiple apps and services."The personal assistant potential looks huge for users of Google services - eg "Give me a summary of my emails today".Moreover, 3rd-party extensions are on the way, starting with Adobe…

17/10/2023
1 perfect prompt to make AI write in your style
medium.com
Card image

To avoid "robotic, cliche AI text that sounds fake" and get "AI-generated content to emulate your unique writing style", you have to feed the AI a sample of your writing. A good prompt:"Based on the tone and writing style in the seed text, create a style guide for a blog or publication that captures the essence of the seed…

01/08/2023
Writing with a Nemesis: Using ChatGPT to Strengthen Your Arguments
thebootstrappedfounder.com
Card image

ChatGPT can be "a highly capable writing partner that never sleeps ... [if you] treat it like an editor, a proofreader, and a disgruntled reader... make it an enemy of my text and let it attack it as vigorously as possible."personal devil's advocate: ask it "to list the top three arguments that someone opposed to my thinking wo…

04/05/2023
How I Built WritingGPT, a Fully Automated AI Writing Team
medium.com
Card image

WritingGPT is an AutoGPT that "simulates an entire writing team, crafting high-quality blog posts [with] only a prompt and a target keyword... articles that provide genuine insights — and that rank on Google.""AutoGPTs are AIs talking to AIs... the output of one AI system as the input for another... chain together multiple AIs, enha…

Text to Diagram in Seconds using ChatGPT
medium.com

"Gantt Chart, Organization, Timelines, Entity Relationship, and Mind Maps Diagram all in less than 1 minute... instruct ChatGPT to come out with the required syntax to generate your diagram ... Generate a <diagram type> in mermaid.js syntax with the following details: <details of the diagram> "

Using ChatGPT to extract intelligent insights from multiple documents
medium.com

"“Document Search Chatbot” ... field common questions (FAQ’s) based on the content of several documents.... Azure Search to extract and rank key highlights from a set of text documents based on a user query. This user query and Azure Search results are then passed to OpenAI to be interpreted and formatted into a chat based response..."Wh…

Two wiki authors and a blogger walk into a bar…
mathewlowry.medium.com
Card image

A repost of one of my experiments with the massive.wiki team, where we "developed an approach ... which simultaneously enriches blogging by adding some of the best aspects of wikis, and allows wikis to better host something resembling blogs."

ChatGPT Explained: A Normie's Guide To How It Works
www.jonstokes.com
Card image

Jon Stokes thinks "people are talking about this chatbot in unhelpful ways... anthropomorphizing ... [and] not working with a practical, productive understanding of what the bot’s main parts are and how they fit together."So he wrote this explainer."At the heart of ChatGPT is a large language model (LLM) that belongs to the family o…

30/03/2023
Design thinking was supposed to fix the world. Where did it go wrong? | MIT Technology Review
www.technologyreview.com
Card image

Good history of design thinking."IDEO’s way of working: a six-step methodology for innovation called design thinking... Key ... was its replicable aesthetic, represented by the Post-it note:... Not too precious, not too permanent... promises a fast-moving, cooperative, egalitarian process", but is also "disruptive, startup-flavored …

How Mermaid diagrams work in Obsidian
medium.com
Card image

Mermaid lets you "creating diagrams using simple markup language... for quickly jotting down a sequence of steps or a set of interconnected relationships. The above diagrams are created with just a couple of lines of code. Other types include pie charts, sequences, gantt, etc.

Visualising with Obsidian
www.sarman.work
Card image

David's "journey trying to visualise relationships in my Obsidian notes" passed via various approaches, including d3, as he tried to create diagrams encapsulating relationships between nodes.He then stumbled upon the obsidian-excalidraw-plugin ... [which] automatically generate Excalidraw diagrams with its Excalidraw Automate featur…

Bing Is a Liar—and It’s Ready to Call the Cops
www.motherjones.com
Card image

When James West "joined a small wave of users granted early access" to the new Bing (I'll call and tag it "BingGPT"), powered by the same LLM behind ChatGPT, which is "a great party trick ... powerful work tool, capable of jumpstarting creativity, automating mundane tasks", he soon "noticed strange inconsist…

ChatGPT Is a Blurry JPEG of the Web
www.newyorker.com

Interesting, illuminating (but contested) metaphor for thinking about LLMs from one of my favourite authors, Ted Chiang:"Think of ChatGPT as a blurry jpeg of all the text on the Web. It retains much of the information... but, if you’re looking for an exact sequence of bits, you won’t find it; all you will ever get is an approximation... nonse…

Manton Reece - Micro.blog Mastodon
www.manton.org

"Micro.blog can now cross-post to a Mastodon user account... Your custom domain on Micro.blog can now be ActivityPub-compatible, so that you can follow and reply to Mastodon users directly on Micro.blog ... someone can follow your blog posts".As a result "you can consolidate your identity and posts back to your own blog at your ow…

Everyone's having a field day with ChatGPT – but nobody knows how it actually works
theconversation.com
Card image

Is ChatGPT creator OpenAI "a potential Google slayer. Why look up something on a search engine when ChatGPT can write a whole paragraph explaining the answer?" It's very capable, but "struggles to distinguish between truth and falsehood... often a persuasive liar... a bit like autocomplete on your phone... trained on pretty muc…

The Mechanical Professor
oneusefulthing.substack.com
Card image

ChatGPT... is going to change our world much sooner than we expect, and much more drastically

Twitter alternative: how Mastodon is designed to be “antiviral”
uxdesign.cc
Card image

Mastodon is "subtly designed to reduce the huge, viral surges of attention we see on Twitter" and others, which have "deformed people’s behavior... coaxed people to constantly try to hack the attentional marketplace... incessantly making posts ... operatically theatrical... enrage ... [other] high-voltage reaction".Hence “antiv…

4 Twitter features Mastodon is better for not having - Scott.mn
scott.mn
Card image

4 ways Mastodon doesn't optimise for enragement.On Mastodon’s "home timeline... posts don’t have metrics ... you have to click through ... makes you judge a post first by its content, rather than the score attached to it... the whole dynamic [being "ratioed"] doesn’t exist... leads to more thoughtful engagement rather than ... …

Protocol | koodos labs
koodoslabs.xyz

A new app and protocol to give "people full control over their interest graphs ... there was no standard, decentralized repository for online media and its derivatives... culture that is readily available for anyone to annotate, remix, compile, create new editions of or link together in archives. Mediagraph [protocol] will let developers buil…

Collective Intelligence Design Challenges (CDL)
canonicaldebatelab.com
Card image

Via FotL I discover "Canonical Debate Lab (CDL)... researchers, developers, and system thinkers who have independently been working on collective intelligence systems for several years... goal is to aggregate contributions of diverse stakeholders into a unified information space, which can be accessed through multiple views... tailored to a s…

New Public's Signals Research
newpublic.org
Card image

New Public "spent two years reviewing the literature and talked to over 100 experts from disciplines ranging from social psychology to urban planning about the qualities of flourishing public, or semi-public, spaces" for their Building better digital public spaces report. The goal: "to support engineers, designers and builders who w…

Plexus demo, scribed
altilunium.my.id
Card image

"I first decided to try scribing the Betaworx Render session on Plexus using Obsidian and try publishing it via GitHub (context). That didn't work, so when I saw [[rtnf md]] I thought I'd give it a whirl... the idea [of Plexus] is simple:post your thoughts into a defined shared brain on Plexus - eg : https://render.plexus.earth/the …

Why You Love Design from Trust. You just don’t know it yet | by Jerry Michalski | Medium
jerrymichalski.medium.com
Card image

Systems with Design from Trust: assume most (not all) people have good intent."initially feel counterintuitive, even risky...social: they rely on human relationships. appealing: once you wrap your head around them, you want more."The discomfort is a symptom of how today's default setting is mistrust: "we’ve internalized the ass…

About Design Patterns
hillside.net
Card image

Good starting point on pattern languages, ends with useful links.As a definition of what a pattern is: "a proven solution to a problem in a context. Each one documents a reusable solution, encapsulates knowledge about successful practices, and provides information about its usefulness and tradeoffs... Connected sets of interrelated patterns …

Integrate podcasts into your second brain with speech-to-text
mathewlowry.medium.com
Card image

A short experiment on getting the most out of podcasts by using speech-to-text engines to create rtanscripts. TL:DR:Welder’s excellent and free; Otter.ai’s got some amazing features, but it’s pricey; just forget Google.

Proof of concept: Excel-managed dynamic knowledge browser
mathewlowry.myhub.ai
Card image

An interactive knowledge visualisation providing a graphical overview of interrelated online concepts, edited dynamically with an Excel file. Featuring an accessible version driven by the same content.

Thinking becoming about thinking to harness the power of knowing what you don’t know (YANSS)
youarenotsosmart.com
Card image

A YANSS interview with Adam Grant, author of Think Again: The Power of Knowing What you Don’t Know. Generally an "extensive exploration of how to rethink your own thinking", including his WorkLife podcast interview of Margaret Atwood on procrastination.(When annotating a podcast I really like a transcript, but there was none for this epi…

Cookies disclaimer

MyHub.ai saves very few cookies onto your device: we need some to monitor site traffic using Google Analytics, while another protects you from a cross-site request forgeries. Nevertheless, you can disable the usage of cookies by changing the settings of your browser. By browsing our website without changing the browser settings, you grant us permission to store that information on your device. More details in our Privacy Policy.