Greg Loughnane

🤖 #unautomatable | Owner/CEO @AIMakerspace

[Greg Loughnane @GregOnLock]

https://t.co/n2gfrmQer7

[Haider. @haider1]

Yann LeCun says LLMs are strongest in domains where language itself is the substrate of reasoning, like math and code

They can solve problems, prove theorems, and write programs — but they are not creative mathematicians, software architects, or computer scientists

"their role is to help humans build"

[Greg Loughnane @GregOnLock]

https://t.co/4wMNVxG7YN

[Greg Loughnane @GregOnLock]

Another banger from @DeepLearningAI

[Greg Loughnane @GregOnLock]

Be the only one who can do what you do.

#unautomatable

[Greg Loughnane @GregOnLock]

"You're not behind... you're just mid build." ~ @JesseItzler

[Jawwwn @jawwwn_]

.@PalmerLuckey’s advice for young founders:

“If you want to work on technology, work for somebody else. If you want to work on nonstop bullshit—start a company.”

“It became clear there were people much better than me at certain things.”

“I had to stop doing the things I liked, and start doing things I was uniquely able to do— running the company, doing fundraising.”

[Greg Loughnane @GregOnLock]

Write letters. Then mail them.

[David Senra @davidsenra]

There’s too many people playing entrepreneur:

[Kai Lentit (e/xcel) @KaiLentit]

In 2026, AI models expire faster than session cache.

[Greg Loughnane @GregOnLock]

it's a start

[John Bantai Naftali @yanabantai]

How to make ChatGPT teach you any skill

[Greg Loughnane @GregOnLock]

Be a process owner, not *simply* a process runner.

#unautomatable

[Greg Loughnane @GregOnLock]

https://t.co/BJ5hCbYQUn

[Greg Loughnane @GregOnLock]

@hwchase17 PREACH

[Greg Loughnane @GregOnLock]

@latkins @PrimeIntellect Can confirm. I am now amped and like the way it feels.

Well played @PrimeIntellect who is your marketing mastermind behind this?

[Greg Loughnane @GregOnLock]

@omarsar0 @llm_wizard right on time babyyyyy

[Greg Loughnane @GregOnLock]

"Marketing is a revenue function, not a creative one."

A great friendly reminder from @ryandeiss

[Greg Loughnane @GregOnLock]

The best judge for your LLM application is your user.

The LLM that judges your LLM application must have its judgement judged (even if only downstream) by a human user.

Abstraction does not remove the need for contact with reality and survival over time.

#unautomatable

[Greg Loughnane @GregOnLock]

@llm_wizard @vasuman The vibbety viiiibbeeeezzzz so essential

[Greg Loughnane @GregOnLock]

- (February 2001) Agile (Context) Manifesto

Tight agent handoffs + HITL over sloppy autonomy

Working application outputs over verbose agent conversations

Goal-aligned agent teams over rigid templates

Frequent compaction & re-planning

Orig: https://t.co/GQUnrMoA9r

[Greg Loughnane @GregOnLock]

(Agile?) Context Engineering for Agents & Multi-Agent Systems, with @llm_wizard, by @AIMakerspace & @MavenHQ

https://t.co/xTDwYtCdCP

Big Takeaways 👇

Foundational Context Engineering references with big main ideas behind each👇

[Greg Loughnane @GregOnLock]

- (March 30, 2025) 12-Factor Agents

Repo: https://t.co/mEETG7YW3r
Talk: https://t.co/6fZwv2jCzo

💡Big idea: own your context window and treat it like prime real estate; minimize “context utilization”