@karpathy The brilliant engineers at my former employer @PromptQL implemented a wiki idea for data-analytics a few months ago. Love your articulation and the implementation!
Andrej Karpathy is who every delusional tech bro in the valley thinks they are and what their marketing messages about solving cancer for humanity try to make us believe, but the real Andrej Karpathy is a force of one and what a guy! Respect!
I am (slowly) re-reading the Tolkien legendarium (of which Lord of the Rings is a small part). The whole body of work is so incredible and there's nothing else like it... it dilutes other worlds of fiction. Wait - your story doesn't have a comprehensive history/mythology spanning multiple ages all the way back to a creation myth as detailed in separate volumes? You didn't first invent new languages and dialects for your characters? You didn't pack it with powerful themes and stories written it in a beautiful, archaic style and compose poems and songs alongside? It didn't take you multiple decades of iteration? And what of all the uncharted territory still remaining? Is Tom Bombadil one of the Ainur. Where are the Entwives. What happened to the two unaccounted Istari. Can we hear more about what it was like in Cuiviénen when the elves first awoke? Or to see the light of the two trees of Valinor. Or of the splendor of the caves of Aglarond.
What's most on my mind though - the Tolkien legendarium is imo a concrete example of a height of culture. Does AI, today or soon, make it easier to reach this high via empowerment in both writing and ideation? Or harder, when quick wins are tempting and ~free, and an independent ability to create is stifled. If such a body of work is made again but now with heavy AI assistance, does it inspire the same wonder? What if thousands of them come out on demand with just a prompt? Why do you feel cheated when you learn that something your read was AI generated? Is it transient or a function of capability? Is it slop? What is slop? Or is wonder inseparable from its own creation myth of a lifelong obsession of a mind like your own? So many questions.
Hot take: AI Assistants are failing us
Despite the buzz, closed-domain AI assistants are falling short. Without reliable, context-aware responses, they’re not ready for serious business use.
Where AI Assistants Fail
Here’s a scenario from a well known sales assistant that’s out there today:
📊 User Query: “What’s the length of my average sales cycle?”
➡️ Assistant Response: “I calculated the average sales cycle length for your opportunities, but there are no results to show.”
The assistant can’t perform a computation. Why? Let’s break it down.
🛑 The Issue: Closed-domain AI assistants rely heavily on search-first RAG methods, making them unsuitable for high-trust applications.
Consider a task like “Find all emails from last week that need follow-ups.” A search-based AI might skip important messages if they lack specific keywords, leaving critical follow-ups unnoticed. When this incomplete data is passed to the language model, the result is unreliable, making these assistants ill-suited for nuanced business queries.
✅ The Solution: Agentic query planning. Instead of rigid keyword search, assistants should gather all relevant emails and then use an LLM to classify follow-ups—just as a person would—ensuring accuracy.
That’s why our AI lab built PromptQL - an agentic, data access API for your AI!
Here’s a look at what we’ve been up to ⤵️
@Navimumpolice, @KarnatakaCops, @GKforKPSC @CyberHelplineToday
I experienced a cybercrime where I was falsely accused of several serious illegal things using my private information and threatening me. Although I didn’t lose any money nor shared any bank details, I am deeply concerned about the misuse of my personal data, including my Aadhar number and current address that they already have. I am the second victim in my network facing this, and I would like to formally lodge a complaint. They contacted me via these ids
- 0087010784264 and
- The Skype ID used was [email protected] (now changed to [email protected]),
and they claimed to be from the Mumbai Cyber Crime Department. I have attached screenshots. Please advise on next steps.
More on the below threads for awareness to readers, if it helps.
1/9
Participated in a kutty citizen protest today and felt its power.
Police had blocked off HAL airport road for VIP movement at peak hour. I was stuck with hundreds of other vehicles on wind tunnel road.
We hear about the underdog disruptor narrative of starting up but there's also a side that we don't talk about - because that's not what we want our idea of entrepreneurship to be.
Which is why watch the @flatheads_in pitch tonight on #SharkTankIndiaS2 - nothing but respect 🙏
Super stoked for this chat! There are changes happening in the API ecosystem faster than one might expect - and I can’t wait to dive deeper and learn more with @a85.
Bring your questions and ideas and join us for this fun chat!
I'm headed to HasuraCon'22 by @HasuraHQ! Register below and join me! Also, check out my custom Hasura avatar 😍 https://t.co/n9nxr6nixL #HasuraCon#GraphQL4everyone
So excited for this 🤓
@vgcerf gave me a sneak peek into an inflection point that we’re already in the midst of and it’s quite something to be thinking about 🤯
Join us!
It's #HasuraCon😈 month! Join us for 3 days of learnings on the future of your dev stack with GraphQL as your Data API!
💡 Incredible keynotes
📣 Exciting product launches
👀 Stories from our users & community
🔧 Live workshops 🔨
Register now 👇
https://t.co/7QILaMZxpj
"The president is here." President Volodymyr Zelensky of Ukraine posted a video on social media showing him standing alongside other government officials, saying that the country’s leaders had not fled Kyiv as Russian forces entered the city. https://t.co/VPxc01QGAG
We are delighted to announce our $100M Series C funding led by Greenoaks. 🤩
This funding will allow us to accelerate the development and adoption of our GraphQL engine to make GraphQL available to everyone. 🚀
https://t.co/wactA51uKo
This was my nephew. I’m searching for folks who can help us draft some solutions to bring safety into the unregulated adventure sports industry. Your help and advice is welcome. Please RT for visibility?
https://t.co/F5TdIJV4bK