Engineered Analytics

VP, Agent Engineering at Alumnus of Capital One and McKinsey. Linked-in:

[Engineered Analytics @data_ase]

Difficult to see the color, but this is actually a circular rainbow halo around the sun

[Michael Kennedy @mkennedy]

Any recommendations on who to invite for a "self-hosted apps" topic on @talkpython?

They don't need to be the creator of a self hosted app necessarily, but Python-leaning and experienced in self-hosting web apps is the key. (You can invite yourself).

[Engineered Analytics @data_ase]

@mkennedy @TalkPython There’s a newsletter sent by the site https://t.co/RVb3Rqmv22 that’s pretty good and might be an option. Might be contactable via mastodon (see bottom of their web page)

[Engineered Analytics @data_ase]

Former team-member of mine built this, which goes towards addressing a lot of the problems I've been running into recently: https://t.co/0lugO81yxn

@pythonbytes - might be worth a mention

[Patrick McKenzie @patio11]

@tr_babb BigCo decided it didn't need engineers and would do everything through system integrators. Japan, Inc and U.S. government software are structurally fubared for basically the same reason.

[Will McGugan @willmcgugan]

Do me a favor. Run this in the Python REPL, and paste a screenshot.

print('1\u200d2')

Try on more than one terminal, if you have them installed.

[Chad Gorshing @cgorshing]

@willmcgugan ghostty, iterm, and terminal on my mbp

[Ejaaz @cryptopunk7213]

so just to recap this week (so far)

- musk industries is real (spacex, tesla, xai merger)

- clawdbot explosion leading to a bankrun on mac minis but then anthropic released their own version

- tesla dropped the bomb they’re halting production on model s and x to scale 1M optimus humanoid robots this year instead

- china dropped the mother of all open source models kimi k2.5 that turn video into production-ready apps but then google dropped a gemini update ON THE SAME DAY that does the same thing gg

- google said fuck it and also launched the worlds greatest world model genie and switched on gemini for 3.8B chrome browser users AND released alpha genome model that one-shots 1M dna base pairs for 3000 researchers across 160 countries AND teased new veo model

- microsoft crushed earnings, launched a new ai chip but stock still tanked 10% because they *only* grew rev 39%

- anthropic round 2X oversubbed raised to 20B 🏌️

- openai raising another $100B, 750B val 🏌️

- intel leaked they’re gonna help produce nvidias next gen feynman gpus - hello americas tsmc

- a robot (built by figure) washed the dishes with zero human interaction

- apple acquired stealth startup for $2B that can lip read - integrating their tech for new ai consumer airpods with cameras and mics

- demis confirms google glass 2.0 coming this summer

fckin hell

[Hugo Bowne-Anderson @hugobowne]

"Much of the industry will be writing less and less [Python] given the agentic-loop productivity benefits of Go and other modern compiled languages." -- @wesmckinn McKinney (creator of pandas)

Wes’ thoughtful (and spicy!) take is well-taken. If agents are doing the writing, human-first ergonomics stop being the bottleneck.

I'm doing a fireside chat with Wes, @apreshill, & Marcel Kornacker tomorrow. It's all about multimodal AI but I'd have to fire myself if I didn't ask Wes about this.

We'd love to see you there.
See comments for links.

[Sherwin Wu @sherwinwu]

Anyone who tries to build an AI agent for an enterprise quickly realizes that context is king, but is still extremely hard to get right.

Internally at OpenAI, we've been trying to solve the context problem for one vertical: data warehouses. And it's starting to work quite well!

[Leah Culver @leahculver]

There is something so surreal about returning from maternity leave to find my job as a software engineer completely changed. In this Mom Era, I now spend half my time holding my baby's hands and the other half holding @claudeai's hands.

[Andrej Karpathy @karpathy]

A few random notes from claude coding quite a bit last few weeks.

Coding workflow. Given the latest lift in LLM coding capability, like many others I rapidly went from about 80% manual+autocomplete coding and 20% agents in November to 80% agent coding and 20% edits+touchups in December. i.e. I really am mostly programming in English now, a bit sheepishly telling the LLM what code to write... in words. It hurts the ego a bit but the power to operate over software in large "code actions" is just too net useful, especially once you adapt to it, configure it, learn to use it, and wrap your head around what it can and cannot do. This is easily the biggest change to my basic coding workflow in ~2 decades of programming and it happened over the course of a few weeks. I'd expect something similar to be happening to well into double digit percent of engineers out there, while the awareness of it in the general population feels well into low single digit percent.

IDEs/agent swarms/fallability. Both the "no need for IDE anymore" hype and the "agent swarm" hype is imo too much for right now. The models definitely still make mistakes and if you have any code you actually care about I would watch them like a hawk, in a nice large IDE on the side. The mistakes have changed a lot - they are not simple syntax errors anymore, they are subtle conceptual errors that a slightly sloppy, hasty junior dev might do. The most common category is that the models make wrong assumptions on your behalf and just run along with them without checking. They also don't manage their confusion, they don't seek clarifications, they don't surface inconsistencies, they don't present tradeoffs, they don't push back when they should, and they are still a little too sycophantic. Things get better in plan mode, but there is some need for a lightweight inline plan mode. They also really like to overcomplicate code and APIs, they bloat abstractions, they don't clean up dead code after themselves, etc. They will implement an inefficient, bloated, brittle construction over 1000 lines of code and it's up to you to be like "umm couldn't you just do this instead?" and they will be like "of course!" and immediately cut it down to 100 lines. They still sometimes change/remove comments and code they don't like or don't sufficiently understand as side effects, even if it is orthogonal to the task at hand. All of this happens despite a few simple attempts to fix it via instructions in CLAUDE . md. Despite all these issues, it is still a net huge improvement and it's very difficult to imagine going back to manual coding. TLDR everyone has their developing flow, my current is a small few CC sessions on the left in ghostty windows/tabs and an IDE on the right for viewing the code + manual edits.

Tenacity. It's so interesting to watch an agent relentlessly work at something. They never get tired, they never get demoralized, they just keep going and trying things where a person would have given up long ago to fight another day. It's a "feel the AGI" moment to watch it struggle with something for a long time just to come out victorious 30 minutes later. You realize that stamina is a core bottleneck to work and that with LLMs in hand it has been dramatically increased.

Speedups. It's not clear how to measure the "speedup" of LLM assistance. Certainly I feel net way faster at what I was going to do, but the main effect is that I do a lot more than I was going to do because 1) I can code up all kinds of things that just wouldn't have been worth coding before and 2) I can approach code that I couldn't work on before because of knowledge/skill issue. So certainly it's speedup, but it's possibly a lot more an expansion.

Leverage. LLMs are exceptionally good at looping until they meet specific goals and this is where most of the "feel the AGI" magic is to be found. Don't tell it what to do, give it success criteria and watch it go. Get it to write tests first and then pass them. Put it in the loop with a browser MCP. Write the naive algorithm that is very likely correct first, then ask it to optimize it while preserving correctness. Change your approach from imperative to declarative to get the agents looping longer and gain leverage.

Fun. I didn't anticipate that with agents programming feels *more* fun because a lot of the fill in the blanks drudgery is removed and what remains is the creative part. I also feel less blocked/stuck (which is not fun) and I experience a lot more courage because there's almost always a way to work hand in hand with it to make some positive progress. I have seen the opposite sentiment from other people too; LLM coding will split up engineers based on those who primarily liked coding and those who primarily liked building.

Atrophy. I've already noticed that I am slowly starting to atrophy my ability to write code manually. Generation (writing code) and discrimination (reading code) are different capabilities in the brain. Largely due to all the little mostly syntactic details involved in programming, you can review code just fine even if you struggle to write it.

Slopacolypse. I am bracing for 2026 as the year of the slopacolypse across all of github, substack, arxiv, X/instagram, and generally all digital media. We're also going to see a lot more AI hype productivity theater (is that even possible?), on the side of actual, real improvements.

Questions. A few of the questions on my mind:
- What happens to the "10X engineer" - the ratio of productivity between the mean and the max engineer? It's quite possible that this grows *a lot*.
- Armed with LLMs, do generalists increasingly outperform specialists? LLMs are a lot better at fill in the blanks (the micro) than grand strategy (the macro).
- What does LLM coding feel like in the future? Is it like playing StarCraft? Playing Factorio? Playing music?
- How much of society is bottlenecked by digital knowledge work?

TLDR Where does this leave us? LLM agent capabilities (Claude & Codex especially) have crossed some kind of threshold of coherence around December 2025 and caused a phase shift in software engineering and closely related. The intelligence part suddenly feels quite a bit ahead of all the rest of it - integrations (tools, knowledge), the necessity for new organizational workflows, processes, diffusion more generally. 2026 is going to be a high energy year as the industry metabolizes the new capability.

[Nicolas Bustamante @nicbstme]

https://t.co/YTBz2tzxiJ

[Rasmussen Reports @Rasmussen_Poll]

Is requiring photo ID to vote a reasonable measure to protect the integrity of elections?

YES -
All Voters: 73%
Men: 69%
Women: 76%
18-29: 70%
30-39: 70%
40-49: 80%
50-64: 77%
65+: 67%
White: 73%
Black: 70%
Hispanic: 69%
Other: 83%
DEM: 64%
IND: 69%
GOP: 86%

[Michael Kennedy @mkennedy]

New essay: Blocking AI crawlers might be a bad idea - Disappearing from AI results won't make #AI go away

https://t.co/kckGRXmhnS

[Michael Kennedy @mkennedy]

New essay: Python Supply Chain Security Made Easy

https://t.co/x7n0KxpKZS

[Michael Kennedy @mkennedy]

Check it out @charliermarsh, another "install via uv" tool :)

https://t.co/ZeGooKazgx

[Michael Kennedy @mkennedy]

Live in 10 min! Join me, @mkennedy, and Vincent D. Warmerdam on @talkpython for Python apps with LLM building blocks. #python #podcast

https://t.co/OwUXhLD96M

[John Arnold @johnarnold]

Santa Clara is one of the first law schools to publish 2026-27 tuition. Historically, Grad PLUS loans have had no limits. Starting next year, professional school borrowing will be capped at $50k/year. Notice anything about the trend in tuition?
I expect many schools to copy this.

[Talk Python Podcast @TalkPython]

Want better, faster #Python typing (cli and IDE)? Use the same tools that the Instagram team uses on their millions of lines of code.

#523: Pyrefly: Fast, IDE-friendly typing for Python

with @javabster, @yangdanny97, Kyle Into, and host @mkennedy

https://t.co/a9jiddUeVv

[Michael Kennedy @mkennedy]

New essay: Primed: Should You Hype Your AI Before You Start?

https://t.co/CCx8BMO9oc