LLMs seems to be O(n!) way of achieving AGI #OpenAI #GPTs

AI is real and it’s already here. I wish coding assistants also have a similar metric.

Agent Design Is Still Hard https://t.co/9FwXRxOCQJ

Don't think of LLMs as entities but as simulators. For example, when exploring a topic, don't ask: "What do you think about xyz"? There is no "you". Next time try: "What would be a good group of people to explore xyz? What would they say?" The LLM can channel/simulate many

"Just tried X—it's incredible!" "Y is officially dead." "If you're not using Z yet, you're behind." This arms race of hype has become the norm. We compete over who can evangelize the latest framework fastest. Compare this to another profession that deals with constant

People say sell shovels in a gold rush. Low risk. Steady demand. But the highest value comes from learning how to spot the gold itself. The ability to map terrain, read signals, and mine with discipline compounds far longer than any tool you sell. In AI and engineering, tools

This is gold! So true!

https://t.co/VfeOkdO6gu

If you are pinging someone who’s busier than you, you should have a single well-thought-out specific ask. Only ask for something you truly cannot do on your own, and where you have done everything you possibly can by yourself. For example, if you’re asking someone to send an

It is impossible to call yourself an experienced infrastructure/distributed systems engineer if you have consistently switched jobs every two years. You become a rockstar engineer by building complex infrastructure, operating them at scale, migrating users, fixing issues and

The same logic applies to Excel. You pay not always because you can't do it, but also because you don't want to.

OpenAI's AgentKit launch shows the industry is still thinking in old paradigms. Visual builders and drag and drop canvases feel like we're recreating no-code tools from a decade ago. The real breakthrough will be a conversational agent that lets you describe what you want in

First Principles Thinking in Software Engineering: The Path to Clarity, Innovation, and Freedom In engineering, complexity grows quietly. Layers of abstraction pile up. Decisions compound. Over time, people stop questioning why things exist and just work around them. That is

PG’s 6 principles for making new things:

Spot on. Also never jump ahead and fix something without understanding why it exists in first place.

I keep observing how a bunch of large companies have *really* smart engineers doing *really* complex+challenging+interesting work and... no one knows about it outside. I only get to know about it by chance. Sometimes it's the PR policies stopping talk about this, but more often:

This is going to be ironic coming from me but the best software engineers I've ever worked with and that you can ever hire are the ones with no online presence, no GitHub activity, and spent the last 10 years of their life working at the most boring company you can ever imagine.

Reducing complexity is the ultimate flex for a software engineer.

Intelligence is mostly about knowing exactly what you are not intelligent about.

Amazon AWS CEO says using AI to replace junior staff is 'Dumbest thing I've ever heard'