Technology

Overheard : AI needs cloud

On The Verge‘s Decoder podcast, Matt Garman, CEO of AWS, explained why AI’s potential is intrinsically tied to the cloud. The scale and complexity of modern AI models demand infrastructure that only major cloud providers can deliver

You’re not going to be able to get a lot of the value that’s promised from AI from a server running in your basement, it’s just not possible. The technology won’t be there, the hardware won’t be there, the models won’t live there, et cetera. And so, in many ways, I think it’s a tailwind to that cloud migration because we see with customers, forget proof of concepts … You can run a proof of concept anywhere. I think the world has proven over the last couple of years you can run lots and lots and lots of proof of concepts, but as soon as you start to think about production, and integrating into your production data, you need that data in the cloud so the models can interact with it and you can have it as part of your system.

January 13, 2025 by business Management OverHeard Technology 0

Agency for AI Agents

Huggingface just released their agentic library to interact with LLMs. I liked the way they define agents.

AI Agents are programs where LLM outputs control the workflow.

And the way they defined the spectrum of agency for the agents

January 6, 2025 by AI Industry Jargon Technology 0

30 day challenge : create software with AI

I like to do 30 day challenges to explore new areas, or to form habits. Some of my previous ones were

I am starting a new challenge today, to create software by leveraging AI. The recent boom in AI and GenAI specifically has made it very easy and quick to bring your ideas to fruition. It is time to start coding and developing software for ideas that have been swirling in my head for sometime.

I will be publishing them at https://kudithipudi.org/lab . I will expand and write up about some ideas and the experience in bringing them to life.

Inspired by https://tools.simonwillison.net/.

November 13, 2024 by AI Technology 0

On AI Agentic Workflows

Amazing conversation with Bret Taylor on agentic workflows leveraging AI in the enterprises. The whole conversation is worth listening to multiple times, but this specific segment where Bret speaks about the difference between traditional software engineering and AI driven solutions was thought provoking on how much change management organizations have to go through to adopt to these new solutions.

Now if you have parts of your system that are built on large language models, those parts are really different than most of the software that we’ve built on in the past. Number one is they’re relatively slow compared — to generate a page view on a website takes nanoseconds at this point, might be slightly exaggerating, down to milliseconds, even with the fastest models, it’s quite slow in the way tokens are emitted.

Number two is it can be relatively expensive. And again, it really varies based on the number of parameters in the model. But again, the marginal cost of that page view is almost zero at this point. You don’t think about it. Your cost as a software platform is almost exclusively in your head count. With AI, you can see the margin pressure that a lot of companies face, particularly of their training models or even doing inference with high-parameter-count models.

Number three is they’re nondeterministic fundamentally, and you can tune certain models to more reliably have the same output for the same input. But by and large, it’s hard to reproduce behaviors on these systems. What gives them creativity also leads to non-determinism.

And so this combination of it, we’ve gone from cheap, deterministic, reliable systems to relatively slow, relatively expensive but very creative systems. And I think it violates a lot of the conventions that software engineers think about — have grown to think about when producing software, and it becomes almost a statistical problem rather than just a methodological problem.

September 11, 2024 by Management Technology 0

HOWTO : Flex your muscles

A tongue in cheek headline :-). The post is not about body muscle, but about how you can flex your market power (muscle).

Here is a screenshot comparison of default apps settings in Microsoft Windows 10 and Windows 11. Notice how instead of just giving one option to change the default browser, Microsoft has moved the option to change it by file extension? Does a layperson even know the difference between htm, html, http and https? A clever way for Microsoft to make it a bit more difficult to switch away from edge (Microsoft’s new Internet browser). Some might even call it sinister 🙂

Update Oct 11 : Looks like the main stream media is catching up on this. The Verge has a post on this topic https://www.theverge.com/22714629/windows-11-microsoft-browser-edge-chrome-firefox

October 9, 2021 by Technology Windows 0

HOWTO : Query json data in SQLite

A self note for querying json data in SQLite. BTW, I think SQLite is an under utilized and under appreciated swiss army tool for data storage and manipulation. And thanks to Richard Hipp, it is free.

If you have a column defined as a json type in your SQLite database, quickest way to search for the data is json_extract. A full set of functions available are documented at https://www.sqlite.org/json1.html

If you have a column named family_details in a table family with the following json in it as an example 

{
	"father": {
		"name": "dad",
		"birthday": "1/1/2000",
		"pet_name": "daddy"
	},
	"mother": {
		"name": "mom",
		"birthday": "1/1/2001",
		"pet_name": "mommy"
	},
	"sons": [
		{
			"name": "son_one",
			"birthday": "1/2/2020",
			"pet_name": "sonny_one"
		},
		{
			"name": "son_two",
			"birthday": "1/2/2021",
			"pet_name": "sonny_two"
		}
	],
	"daughters": [
		{
			"name": "princess_one",
			"birthday": "1/2/2020",
			"pet_name": "princy_one"
		},
		{
			"name": "princess_two",
			"birthday": "1/2/2021",
			"pet_name": "princy_two"
		}
	]
}

and you want to print the name of the father, you can use

select json_extract(family_details, '$.father.name') as father_name
from family

json_extract uses the name of the column and the json node as parameters. In this case, we used $(which denotes the root), father and name (under father) as the json node.

April 13, 2021 by Databases HOWTO Technology 0

Collection of tools to serve local content on your workstation to the Internet

A quick collection of tools you can use to serve/publish content/applications on your local dev to the Interwebs. Some use cases for these types of tools..

  • Developed a static website and want to show it someone that is not right next to you.
  • Developed an API that you want an app or user to access from the web

List of tools:

  • https://ngrok.com/ : Most popular tool for this purpose. the free tier is enough for most use cases.
  • https://tunnelto.dev/ : Latest entrant in this space. In addition to have a paid hosted service, you can run this for free on your own server. But that defeats the pupose of having a tool to use in a pinch to share content :).
  • http://pagekite.net/ : Been around for 10+ years. Similar to tunnelto.dev, you can run this on you own server or pay (very nominal price) for the hosted service.

June 25, 2020 by Technology Web 1