agingmillennial

Sass as a service.

[agingmillennial @agingmillennial]

@Appyg99 I'd almost agree with this if TSA pre was consistently faster than regular lines. SFO is uniquely the opposite of this.

[Aaron Levie @levie]

Just coming off of meetings with a couple dozen enterprise IT leaders discussing AI agents. Here are a few of the common themes that stand out:

* Lots of conversation that you have to solve an operating model challenge to get the full benefits of AI. Most companies have orgs that have always operated in siloes; but agents are most effectively when they are tied to a process, which often cuts across these siloes. So the big question is how do you start to deploy centrally managed agents that can work across organizational boundaries. Who manages these agents? How do they get deployed and adopted?

* Data fragmentation remains a major issue for most organizations. As long as data remains highly fragmented and not in standard formats, or data is not available to the right people and agents, enterprises are dealing with issues around being able to get answers from agents that are accurate or that conform to their business practices. This cuts across both systems with structured data (product metrics or revenue figures) and unstructured data (product roadmap or customer contracts).

* Clear sense that companies need to figure out what their core data moats are going to be in the future. If everyone has access to roughly the same superintelligence from the various models, then the context that you feed the models becomes proprietary value in the future. Capturing this data and getting it into a format that agents can use becomes very important.

* Everyone is trying to figure out the right metrics to manage to for AI adoption. General consensus that tokens are not the right metric per se, and people leaning more toward business outcomes (in an ideal world). For business outcomes (like more revenue or more shipped product), though, you have to get close to each individual workflow to figure out if it was successfully transformed with AI so it’s harder to manage top down.

* Growing view that enterprises are going to live in a multi-model world. Lots of interest (though early in actual adoption) in layers that can route workloads to different models (frontside or open weights) for cost or performance reasons. Also enterprises are trying to figure out what things do you give to the models directly vs. what do you separate as horizontal systems and context so you can swap any system in and out.

* Talent for driving AI adoption and implementation still remains a major issue and topic. Many view it as something you necessarily have to train for internally due to a shortage of talent being trained on this in the outside. As an aside, this feels like it remains a huge opportunity for those that get very good at deploying and management agents in an enterprise since most companies are looking for these skills.

* The best use-cases for AI tend to be those that fundamentally change the work being done instead of just replacing an existing process and doing it more efficiently. Companies are working through their versions of this individually because it’s different per industry, but this often remains both the most exciting and higher upside uses of AI.

Many more topics discussed recently, but overall it’s clear that there’s a ton of change going on with much more to come.

[Andrej Karpathy @karpathy]

LLM Knowledge Bases

Something I'm finding very useful recently: using LLMs to build personal knowledge bases for various topics of research interest. In this way, a large fraction of my recent token throughput is going less into manipulating code, and more into manipulating knowledge (stored as markdown and images). The latest LLMs are quite good at it. So:

Data ingest:
I index source documents (articles, papers, repos, datasets, images, etc.) into a raw/ directory, then I use an LLM to incrementally "compile" a wiki, which is just a collection of .md files in a directory structure. The wiki includes summaries of all the data in raw/, backlinks, and then it categorizes data into concepts, writes articles for them, and links them all. To convert web articles into .md files I like to use the Obsidian Web Clipper extension, and then I also use a hotkey to download all the related images to local so that my LLM can easily reference them.

IDE:
I use Obsidian as the IDE "frontend" where I can view the raw data, the the compiled wiki, and the derived visualizations. Important to note that the LLM writes and maintains all of the data of the wiki, I rarely touch it directly. I've played with a few Obsidian plugins to render and view data in other ways (e.g. Marp for slides).

Q&A:
Where things get interesting is that once your wiki is big enough (e.g. mine on some recent research is ~100 articles and ~400K words), you can ask your LLM agent all kinds of complex questions against the wiki, and it will go off, research the answers, etc. I thought I had to reach for fancy RAG, but the LLM has been pretty good about auto-maintaining index files and brief summaries of all the documents and it reads all the important related data fairly easily at this ~small scale.

Output:
Instead of getting answers in text/terminal, I like to have it render markdown files for me, or slide shows (Marp format), or matplotlib images, all of which I then view again in Obsidian. You can imagine many other visual output formats depending on the query. Often, I end up "filing" the outputs back into the wiki to enhance it for further queries. So my own explorations and queries always "add up" in the knowledge base.

Linting:
I've run some LLM "health checks" over the wiki to e.g. find inconsistent data, impute missing data (with web searchers), find interesting connections for new article candidates, etc., to incrementally clean up the wiki and enhance its overall data integrity. The LLMs are quite good at suggesting further questions to ask and look into.

Extra tools:
I find myself developing additional tools to process the data, e.g. I vibe coded a small and naive search engine over the wiki, which I both use directly (in a web ui), but more often I want to hand it off to an LLM via CLI as a tool for larger queries.

Further explorations:
As the repo grows, the natural desire is to also think about synthetic data generation + finetuning to have your LLM "know" the data in its weights instead of just context windows.

TLDR: raw data from a given number of sources is collected, then compiled by an LLM into a .md wiki, then operated on by various CLIs by the LLM to do Q&A and to incrementally enhance the wiki, and all of it viewable in Obsidian. You rarely ever write or edit the wiki manually, it's the domain of the LLM. I think there is room here for an incredible new product instead of a hacky collection of scripts.

[agingmillennial @agingmillennial]

@pjux Relevant - https://t.co/EbknGPjfJS

[Moira Donegan @MoiraDonegan]

Right wing men desire a world ruled by hierarchy and domination, and the way they treat women and girls is an extension of that principle.

Left wing men desire a world ruled by equality and dignity, and the way they treat women and girls is an exception to that principle.

[Peter Yang @petergyang]

Two great engineers reflecting on how the profession is fundamentally changing with AI

[agingmillennial @agingmillennial]

@melissa Fantastic thread, thank you!

[agingmillennial @agingmillennial]

@BolourNoah @MarmotRespecter The core of it is actually the family's social status. Family's well-being is completely optional. Corrected it for you.

[agingmillennial @agingmillennial]

@AliceFromQueens same with Vance actually

[agingmillennial @agingmillennial]

@anuatluru @AdmaniExplains it's the anxiety of being able to see too far too soon. Hence the whole "live in the moment" and "take it by the day"

[agingmillennial @agingmillennial]

@RichardHanania Somehow "maximizing value for shareholders" does not have the same emotional gravitas as "trying to make the world better".

Libertarianism has always had a PR problem.

[agingmillennial @agingmillennial]

@clairekart @shaunmmaguire 😂

[agingmillennial @agingmillennial]

@mattyglesias The bar has been set so low that we will take performative empathy is like a Black Mirror episode happening in real time

[agingmillennial @agingmillennial]

@rsvptemple You mean we will never see a Gen Alpha comedian making fun of their Millennial parents? Big sad 😭

[agingmillennial @agingmillennial]

@pourfairelevide TLDR; Follow the market, follow the money. Purpose comes later when your basic needs are met.

[agingmillennial @agingmillennial]

You are missing a key point that for the duration the fun lasted, poor people became wealthy because of the tech boom and they *now* have enough cushion to not have to worry so much about the rug pull

Doing what you like early on may never give you that kind of buffer, it's a huge gamble to take without understanding the risks involved.

[agingmillennial @agingmillennial]

@agarwal Thank you for all the hard work ❤️

[agingmillennial @agingmillennial]

@LittleMammith No it's good they out themselves out of the gene pool early on.

[agingmillennial @agingmillennial]

@MoiraDonegan oooof could not have said it better

[agingmillennial @agingmillennial]

Yep, you can't replace racism with another thinly veiled form of racism and group generalizations. As a South Asian, it's particularly jarring to hear that Asian culture is somehow 'superior' and that Tiger Moms produce meritocracy. The natural line of questioning from this point would be: why do we even need to leave our respective countries?

IMHO, the South Asian-Americans who are thriving are the ones who have successfully integrated the good parts and rejected the bad parts of both cultures.

JD Vance gets it. Vivek just made the cringiest bad faith argument.

[agingmillennial @agingmillennial]

@river_is_nice Amen