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
Technology
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/.
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.
AI & Humans
AI will not replace humans but humans who use AI will replace humans that don’t – Dr. Fei-Fei Li
Disaster Recover vs Business Continuity
Really liked this simple explanation on the difference between BDR and BCP shared in a hacker news discussion
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
HOWTO : SQL Joins
A simple and useful visual of joins in SQL by Taylor Brownlow from this post https://towardsdatascience.com/take-your-sql-from-good-to-great-part-3-687d797d1ede
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 $(which denotes the root), father and name (under father) as the json node.
Collection of tools to serve local content on your workstation to the Internet
A quick collection of tools you can use to serve/publish content/applications on your local dev to the Interwebs. Some use cases for these types of tools..
- Developed a static website and want to show it someone that is not right next to you.
- Developed an API that you want an app or user to access from the web
List of tools:
- https://ngrok.com/ : Most popular tool for this purpose. the free tier is enough for most use cases.
- https://tunnelto.dev/ : Latest entrant in this space. In addition to have a paid hosted service, you can run this for free on your own server. But that defeats the pupose of having a tool to use in a pinch to share content :).
- http://pagekite.net/ : Been around for 10+ years. Similar to tunnelto.dev, you can run this on you own server or pay (very nominal price) for the hosted service.
HOW TO : Add commas (,) at the end of every line using Notepad++
Thanks for this great nugget from Sumama Waheed
Many a time, you get some data as a CSV file and need to copy some of that data and include it in a SQL statement. For instance one of the rows in the CSV was first name in the format below
employee_id 1234 8765 9808 1235 8734 6723
And you need to put it in a SQL statement as below
SELECT * FROM employee_table WHERE employee_table.employee_id IN (1234, 8765, 9808, 1235, 8734, 6723)
That’s a lot of adding commas (,) at the end of every line. You can do it quickly in Notepad++ (you can do the same in any editor that supports regex) using the regex capability in search and replace using ($) as the search string and $, as the replace string.
