wj

Exactly! I called that the Operations Equation and wrote a tiny bit more here about it: https://zero2data.substack.com/p/the-operations-equation

Once you are inserting models into non-creative (and software development is creative work) it is imperative to start creating your own small evals. Not just to check how different models perform in that equation, but to catch model drift over time.

Software engineering is a sliver of overall economic output. It is an input for tech companies who sell something else (ads, subscriptions, etc.). It is a backoffice expense for non-tech firms that do engineering.

I anticipate that the harness (and memory) will evolve far more outside of engineering. Muse/Dots are an example of that.

I've been writing about this thesis for the past year or so and here is a bit of a summary of where I think it is going: https://zero2data.substack.com/p/the-future-of-consumer-ai

The moat isn't going to be the model (short of AGI). The moat is going to be what surrounds it. The harness and, I have suggested elsewhere, memory. The more personalized the AI is to you the more valuable it will be.

Also, as tech companies grow, a significant portion of the dev body count is for internal tooling. I was always flabbergasted at Twitter's headcount growth back in the day when it seemed like the only innovation increasing the number of characters in a tweet.

Right now we are in a weird spot where a lot of people are flailing around inside corporate America trying to figure out how to leverage AI. Few have enough vision to see what the companies of the future will look like and work towards that.

I have a few core observations about work that influence how I approach AI:

1. There is one-time work (development, personal assistant) where the input and output are net new. There is also back office work (billing, FP&A, questions about data) that is quite repetitive--working within existing datasets.

2. Back office work exists within SaaS products all of which are including AI within their platforms. Those SaaS products are often integrated with each other.

3. Business logic needs to be transferred between systems in order for each SaaS AI to be accurate. (Asking a Salesforce AI and a Xero AI "What is our revenue?" may get you different answers if either system has custom logic that defines any input to that question differently.)

Based on this, I believe that the optimal path forward for back office work is:

1. Centralize agents (business logic) across an organization

2. Decouple agents from orchestration

Agents that exist at the end of an API call--which can be from a SaaS, Airflow, vibe-coded app, or model harness--are a better answer than platform specific AI. They provide a centralized repository for business logic while reducing vendor reliance (and lock in). Additionally, you get better observability and auditabilty.

Sleeper Service is the result of this thinking--an enterprise AI framework.

Larger write up of my thought process behind Sleeper Service here: https://zero2data.substack.com/p/agents-as-a-service

That was the idea that stuck with me the most from the novel. I did a bit of a surface level dig into what that would look like:;

https://www.startuplevelup.com/corporations-as-an-api/

What I think is missing is the lineage of an agent's identity. A public key maybe?

I see that as well. Sometimes I can see that they are prioritizing speed to print for breaking news (publishing to the web happens continuously vs the cadence of a daily newspaper) but often it is just being sloppy.

When most people are consuming _their_ news (as opposed to _the_ news) in the form of a thumbnail in an algorithmic social media feed, those copy errors matter less.

How is this different from Microsoft scraping to build Bing?

Honest question. There is a line in the sand somewhere apparently.

Every once in a while I would put Flight Simulator 2020 on my desktop and work on my laptop. I found that watching the digital world pass by while working put me in a slightly different headspace. Not sure it increased productivity but working while sitting in an actual plane does provide me a bit of focus.

Train ride videos on YouTube scratch some of the same itch.

The Weber kettle grill is one of my favorite examples of quality in another way—function. It is built well but it also is such a wonderfully simple design that provides quite a bit of flexibility.

I have the Smokey Mountain which is amazing at holding heat but a total PIA to clean. Have one of their gas grills as well on a built in line, and it is fairly high quality also.

Nothing tops the kettle though.

Is that self reported? Does it apply to content created by a U.S. based AI model? Posted on a U.S. website? Read by someone in the U.S.

I am not anticipating people self identifying slop.

I don’t want to read content written by AI.

A feature I would like on LinkedIn would be a 100% verified human content flag for users. LinkedIn can then do the scans and flip that to false for any users it catches posting AI assisted content. Let me filter that out of the feed.

If we don’t do something to maintain some standard of discourse, we lose intellectually and as a piece of our humanity.

LinkedIn is the only social media I use and it is on thin ice.

When I moved from LA to St Louis many years ago, there wasn’t an IKEA yet. I was truly confused about where one was supposed to go to buy lamps. Any furniture stores that had them were selling ones that gave off strong grandma vibes.

Very much agree on Fable. Over the past month or so it has shown to be the only Anthropic model that can understand a largish dbt model codebase. Opus 5 gets almost everything wrong. (High reasoning on both)

That brought to mind this examination of Taylor Swift's Shake it Off:

https://www.mcsweeneys.net/articles/taylor-swift-a-socratic-...

I tried zed for its vertical agent threads grouped by project (which Claude Code has since added) and had the same experience--even after trying a bunch of different themes. It felt like none of the dark themes had enough text contrast.

Maybe my eyes are just getting worse...

What is the timeline you expect for this?

Brooks bears are wonderful. The sound is calming. I also like Surfline:

https://www.youtube.com/live/hm9iAviOZ20?is=zkOMcU_8Sck0LOer

Me: 46 | M | NYC/St. Louis | Father. Interested. Enjoy browsing bookstores, economic podcasts, nature. Variety is the spice of life. Work too much...

Ideal Partner: 35-55 | F | NYC/St. Louis | Ambitious, academic, or artistic -- someone who is intrinsically driven to learn or create

I did a quick comparison of models a couple of months ago by giving it a MYTXTADV.BAS file and give them all the same prompt to create a sprite-based version of a text adventure game I wrote in Basic over 30 years ago.

It was interesting to see where the approaches were similar and where they diverged.

True about AI slop pre-AI. Before 2026 my LinkedIn feed was mostly about how to get rich buying real estate. AI is an improvement.

I would like to remove the AI-generated content and any low-effort content from my LinkedIn feed. There can be some great stuff in there but a lot of it isn't worth my attention. Probably going to explore some browser plugins with that because the algorithm doesn't seem to do the best job giving me content that is interesting to me. It may be giving me topics I enjoy reading about now (AI) but not the level of "thought leadership" I want. Substack is better for that these days.

I write both places because I enjoy writing.

This seems like something MLB teams would install in their locker rooms if it works.

I felt that Amazon had the best chance to step into the ticketing game as they have the platform that can handle the volume spikes (Cyber Monday). But tech infrastructure is only a part of the puzzle.

I think because so much of an idea is shaped by the language used to convey it, it may be hard to separate the person from the LLM.

I think gp may want to know if a <person> has an interesting idea rather than <person + llm>.

He was a big supporter of the Democratic Party which would not necessarily lead to a pardon with the Republican administration.

I swear my hearing got more sensitive with kids. Also, some commercials hit differently.

You’re right. Books like the Four Hour Workweek and Escape From Cubicle Nation were guides to passive income twenty years ago.

I'm not sure I understand your last paragraph? The two sentences seem to contradict?