Tyler Morgan

I mostly run a farm, but I also still enjoy tinkering with code and thinking about mining.

Owner of and

[Tyler Morgan @TylerMorganMe]

@henrytdowling Some of the harnesses are open source, but the infra layer behind them is all kinds of opaque. 4.6 today may or may not perform like 4.6 tomorrow. The same goes for anything else that's not open weight.

[Tyler Morgan @TylerMorganMe]

The two biggest features I want for AI models:
- version-controlled harness and model selection
- a quick way to let me opt in and out of different memory layers on the fly

Cross-project memory layers are really useful in certain scenarios and entirely counterproductive in others

[Tyler Morgan @TylerMorganMe]

Is it just me, or is Claude using the phrase "belt-and-suspenders" like GPT uses the em dash?

[Tyler Morgan @TylerMorganMe]

@icanvardar Crop plan for a small farm. Trust me, I've tried.

[Tyler Morgan @TylerMorganMe]

Having worked in the farming and mining industries (two major users of water in most states), I'm pretty sure data centers represent a drop in the bucket.

Agreed that there are still all kinds of fun issues with data centers, but I think the water is overstated.

[ThePrimeagen @ThePrimeagen]

It's crazy the anti-ai data center people keep talking about water usage.

Talk about noise pollution, electricity issues, security, anything but water issues.

All the data centers is equivalent to ~10 acres of corn.

[Massimo @Rainmaker1973]

No gas, no noise, just pure efficiency.

This man and his scythe are unstoppable.

[Tyler Morgan @TylerMorganMe]

Try Gemini again. Claude and GPT seem to have some regression, but Gemini seems to have kept cooking in the background.

[Tyler Morgan @TylerMorganMe]

Why did we decide that markdown wasn't the best option for LLM outputs?

[Tyler Morgan @TylerMorganMe]

Using auto as my baseline with dangerously skip permissions when I need it feels so nice.

[Tyler Morgan @TylerMorganMe]

@simonw Increasingly, I find that they aren't even searching and just making it sound like they do. But maybe that's just the voice versions.

[Tyler Morgan @TylerMorganMe]

Back in 2013, I set a goal to "do something" programming-related for 100 days straight. Watch a tutorial, write some code, read an article.

Anything. Just make a little progress.

I hand-drew a calendar on my wall and checked it off every day.

I've been a professional developer for over a decade now.

[ThePrimeagen @ThePrimeagen]

it's crazy how many people think that 30 minutes a day isn't enough to learn anything.

Who told you this? Unknown knowns are wild. People just ingrain hurdles in their head about the universe because some thought leader spoke into their life in the distant past.

[Tyler Morgan @TylerMorganMe]

Whoever decided buttons should be hidden until hover should get a demerit badge

[Tyler Morgan @TylerMorganMe]

passive aggressive

[Tyler Morgan @TylerMorganMe]

What's interesting is how much this reads like the same issues firms have been facing against digital transformation for 20 years.

This all basically boils down to data management and communication issues.

Luckily, AI is pretty high leverage for addressing both.

[Alex Lieberman @businessbarista]

I've been asking $100m+ company execs one question:

"What is the #1 thing slowing/stopping your company's AI transformation?"

A non-exhaustive list of responses:

1) Data quality and connectivity of systems. Plus systems that play nice with AI.
2) Lack of leadership buy-in and implementation
3) Data governance restrictions.
4) Willingness of staff to adopt AI.
5) Incurious culture. Lack of knowledge of the current state of AI
6) Tooling doesn't have API access; team is still learning how to use LLMs.
7) Industry regulation/privacy.
8) Data quality and lack of a comprehensive AI system across the full company.
9) Unclear ownership across teams.
10) Time to actually build solutions.
11) Mixed AI literacy levels across teams.
12) No clear strategy / I'm starting the initiative from scratch.
13) Quality output.
14) Upskilling developers.
15) Silos.
16) Data Security and Security Guideline unclear.
17) Lack of training.
18) Data quality is unclear across multi-product teams.
19) Time.

What would your answer be to this question?

[Tyler Morgan @TylerMorganMe]

@mattpocockuk I put together an anti-pattern skill last week for React, and so far, so good.

[Tyler Morgan @TylerMorganMe]

@mhp_guy Codex is surprisingly good. Was about to cancel before it came out.

[Tyler Morgan @TylerMorganMe]

This blog from @steipete is the closest thing I've seen to a user manual for modern, pragmatic, agent-driven development.

https://t.co/G3Vg6SknbY

[Tyler Morgan @TylerMorganMe]

@mcuban I remember hearing someone say, "We love programs, when really we should just redistribute resources."

[Tyler Morgan @TylerMorganMe]

digital nesting

[ThePrimeagen @ThePrimeagen]

This is a very apt thing

I have noticed a certain malaise i am seeing. it honestly reminds me a lot of 2021 neovim config andies.

You can build anything, just some time and some prompts and you got your fully custom piece of tech for exactly what you want!!

but wait, here is another thing to optimize! wait... there is another thing..

oh no! your first thing doesn't quite do it the way you want it to, better fix that...

...

pretty soon you are having 8 agents building all sorts of stuff and you consistently feel like you are going no where and you have nothing to show for it, yet your brain is moving at 100x the speed, your sleep is suffering, your attention with your kids and wife are dwindling... but bro, just one more prompt, just one more prompt and it will fix this issue, i swear

The burden of being able to build anything is the burden of having to maintain everything and in the day and age of vibing, contracts are even less held tight and change is even faster.

[Tyler Morgan @TylerMorganMe]

I love all the talk around subscription fatigue, and I'm just out here collecting $200 subscriptions like Pokémon cards right now lol