We'll be spending a lot more time trying to understand the outputs of language models. A few thoughts, tips & tricks:
Writing. Something I've had success with: Ask your LLM to explain something in ASD-STE100, it's a controlled language specification originally developed for aerospace maintenance documentation. LLMs well-versed in this language and it comes with heavy constraints on clean writing style that I often find a lot more readable. Sometimes I've tried to soften it a bit e.g. ask for "80% of the way to ASD-STE100" because the spec is quite stringent. But even better:
Diagrams / images. Instead of writing, ask your LLM to create a diagram. These can be a lot easier to process, parse, and understand. But even better:
Web pages. Ask for output "in HTML" to get a beautiful, interactive webpage. LLMs are getting really good at frontend and can create beautiful experiences, animations, etc. But even better:
Explainer videos. The output format I am most bullish on is fully custom / bespoke explainer videos generated on any arbitrary topic. Experiment with things like "Create a 3b1b style video explainer on X. Use my ElevenLabs API key for audio narration". (you'd need an API key for the latter or you can ask your LLM to find you decent free alternatives that use your local compute). This is actually starting to work!
In summary:
- As LLMs get better, they will do more and more of the legwork autonomously, and a lot more of our work will rise up the abstractions into oversight and understanding.
- Luckily, LLMs can help here too because as intelligence and code are increasingly abundant, you can ask for large, custom, discardable software artifacts (e.g. web apps, video explainers) that would have never made sense to create before. Push the boundaries here and you'll be surprised.
@paraschopra https://t.co/a9TvXRhAx1 co-founder Hemant (DCE alumni, BLR based) organised a 3 day trek for us last October in Uttarakhand. It was an awesome experience all round including detailed pre-trek briefings. Highly recommended.
Scott Aaronson on practical quantum speedups:
"Billions of dollars are being invested in quantum computing in hopes to accelerate machine learning, optimization, finance, AI. As a quantum algorithms person, honesty compels me to report that the situation is much, much iffier."
Is recruitment fraud a big deal - well, it seems to be. Read on!
Countering Recruitment Fraud: The Power of Qryptal's Secure QR Codes https://t.co/kdZTnNeYS2
@amitranjan Thanks for the summary. Share your concerns on standardization and interoperability being an afterthought.
Though for Covid vaccination certs: EU-DCC has become a de facto standard and is being used by 75+ countries today: https://t.co/ChPAAYxwgf
Get inside the biggest acquisition of Facebook's history: WhatsApp. @AimeePKeane
With insights from former chief business officer Neeraj Arora https://t.co/BCNGWELxyq
You can listen to @vinodvasnani speaking on Integrating Sustainability and Financial Inclusion to Drive Economic Growth on 27 October 2022 @11:30GMT. Visit https://t.co/ubFDy7cAwp to attend. Don't miss it! @nikj@rajeshsound@qryptal@StanChart
This MIT CS class teaches you things that all the other classes don't teach you, like...
🖥️ Shell tools and scripting
🖥️ Vim
🖥️ Data wrangling
🖥️ Command-line environment
🖥️ Version control
Watch all 11 lectures for free here: https://t.co/oc0tr2z07V
The global #digitalsignature market is USD 4.05 billion today, which will be USD 35.03 billion in 2029. Here are the biggest problems with #DigitalSigning and how you can fix them (Thread)
In 2014, I was the Chief Business Officer of WhatsApp.
And I helped negotiate the $22 billion sale to Facebook.
Today, I regret it.
Here’s where things went wrong:
Here’s my story about @halloapp, a startup cofounded ex WhatsApp execs including @neerajarora, and how the service represents a new way of thinking about social media: smaller, fewer features, & a lot more friction. https://t.co/P1r8A0H1uD
Our most recent HalloApp update allows users to make end-to-end encrypted Audio & Video calls to each other.
Calls can be made to anyone in your phone address book who also has HalloApp installed.
Read more here:
No one is paying the log4j2 maintainers!?
There is a whole page on the responsibilities of a @TheASF "Project Management Committee"... AND NO ONE IS PAYING THEM? https://t.co/JXimIQLxw5
Open Source needs to grow the hell up. Yesterday.
https://t.co/tQpITt8vn3