Rajavel Thiruvu I went on stage, enabled ChatGPT's voice mode, and had IT deliver the bulk of the talk instead of me. Why should the audience have all the fun? 😉

Sandeep Bhat are you sure it's not pen and TABLET? ☺️

They're looking at the schedule, taking notes, reading the slides, chatting on WhatsApp, and taking pictures of slides.

Also noting what other people are doing, in my case.

Wow. Every SINGLE person in the audience at this (Healthcare Education, Singapore) conference was on a laptop, tablet, or mobile. Some on multiple devices.

I guess this is the new model of learning and listening.

The only people who were NOT on a device were on stage. The speakers.

I guess it's up to me to fix that 🙂

Maybe. Someone who takes shortcuts learns less.

Maybe not. Someone who follows rules won't think outside the box.

Both creativity and diligence have their place. People strong in one might benefit from the other.

`Play Devil's advocate to the user, beginning with "Playing Devil's Advocate, ..."`

That's my custom instruction to #ChatGPT. But that's given a sassy personality to the LLM.

Could you make these slides more information-rich", I asked.
Playing Devil's Advocate, maybe you're overfilling each slide," it warns.

How an AI might share the stage with me?", I asked.
Playing Devil's Advocate, what happens when the AI cracks jokes quicker than you can?" it counters.

Suggest hobbies that match my interest," I asked
Playing Devil's Advocate, maybe you're too busy scrolling social media for any real hobbies" it retorts!

These are actual replies. Link: https://lnkd.in/gHm6kW2v

Have any of you ever seen your tech develop a personality?
Have any custom instructions have sparked unexpected replies?

What if AI steals your spotlight?

I co-hosted a panel with ChatGPT and ... it stole MY show!

From hilarious mix-ups like accidental comedy to insightful AI hacks for everyday tasks, #ChatGPT kept the audience engaged and entertained.

What I learned was:

- #AI as can be a very insightful co-host - and an even better comedian sidekick
- Preparation is crucial. Pick the right model and voice mode (E.g. o1 on ChatGPT's standard, not advanced, voice mode)

Full article: https://lnkd.in/gAxAjm-t
Video: https://lnkd.in/gDQRrm-Y

#TechHumor #Innovation #Education

Anshul Chhabra Oh, certainly. But why hurt their feelings? 😉

I totally failed to build an app only using LLMs.

Zohaib Rauf built a series of apps by spec-ing them on ChatGPT and coding them on Cursor. https://lnkd.in/gbBPvZKu

I was inspired and tried that.

Both steps were a failure. I started writing the prompt for the spec, and ended up spending 90 minutes writing the entire spec manually.

Then I prompted Cursor to build the app from the spec. It mixed up frameworks, using React code with lit-html and I had to rewrite step by step.

My learnings: I've a long way to go in LLM-speccing and in building mid-sized apps at one go.

More details: https://lnkd.in/gqQ63xhQ

Navin Kabra oh, yes, this is an excellent source. Thanks!

Janardhan Santhanam - true. I HAVE been pondering this. What do you think are the domains or areas, other than finances and relationships, that compound?

In 2024, I made 3 resolutions.

✅ COMPOUND LONG TERM GOALS, DAILY. I did this in 6 areas:
1. Blogging: https://s-anand.net/
2. Publishing weekly notes: https://lnkd.in/gDqyX4Us
3. Teaching: https://tds.s-anand.net/
4. Reading Manga: https://lnkd.in/gdhb7QY5
5. Building LLM applications: https://lnkd.in/gFTM9w-z
6. Evangelizing LLMs via a portal: https://lnkd.in/gRr4qdYn

❌ HIT 80 HEART POINTS, DAILY. I stopped exercise in the second half and gained 7 kgs.

✅ BE A BETTER HUSBAND. My wife confirmed that I was “definitely worse in 2023 than 2024.”

My most memorable events were:

- Becoming an LLM psychologist: https://lnkd.in/gipEyfyn
- Evaluating assignments with LLMs: https://lnkd.in/gsfx7yiH
- Generating Calvin & Hobbes strips: https://lnkd.in/gz65F4xY

For 2025, I'm taking a slightly different approach to goal setting: https://lnkd.in/gpPt4RgB

Barring a few edge cases, all new work our team does (broadly NLP & computer vision) is handled faster, cheaper, and better with Gen AI. I've asked the team to stop wasting their time with classical AI.

I'm still exploring where to pick up Gen AI expertise from. My learnings at https://tds.s-anand.net/#/large-language-models