jtfrench

This article was a bit confusing for me. It starts off by describing what "doing it wrong" looks like (okay). It then goes on to talk about Agents. Perhaps it's just that my human brain needs a firmware update, but I was expecting the "what doing it wrong looks like" section to be followed by a "what doing it right looks like" section. Instead, the next paragraph just begins with "Agents".

Sure, one could surmise that perhaps "doing it right" means "using Agents", but that's not even how the article reads:

> "To make AI development work for you, you’ll need to provide your AI assistant with two things: the proper context and specific instructions (prompts) on how to behave under certain circumstances."

This, to me, doesn't necessitate the usage of agents, so to then enter a section of agents seems to be skipping over a potentially-implied logical connection between the problem in the "doing it wrong" section and how that is solved in the "Agents" section.

Copying code snippets into web UIs and testing manually is slow and clunky, but Agents are essentially just automations around these same core actions. I feel this article could've made a stronger point by getting at the core of what it means to do it wrong.

• Is "doing it wrong" indicated by the time wasted by not using an agentic mechanism vs manual manipulation?

• Is "doing it wrong" indicated by manually switching between tools instead of using MCP to automate tool delegation?

Having written several non-trivial agents myself using Gemini and OpenAI's APIs, the main difference between handing off a task to an agent and manually copy/pasting into chat UIs is efficiency — I usually first do a task manually using chat UIs, but once I have a pattern established, or have identified a set of tools to validate responses, I can then "agentify" it if it's something I need to do repeatedly. But the quality of both approaches is still dependent on the same core principles: adequate context (no more nor less than what keeps the LLM's attention on the task at hand) and adequate instructions for the task (often with a handful of examples). In this regard, I agree with the author, as correct context + instructions are the key ingredients to a useful response. The agentic element is an efficiency layer on top of those key ingredients which frees up the dev from having to manually orchestrate, and potentially avoids human error (and potentially introduces LLM error).

Am I missing something here?

My gut says similar. They've been on a roll. Genie 3 looks pretty wild.

Word on the street is that non-existent code doesn't crash.

Bodes well this does not.

My thoughts exactly.

awkward

>>>"The biggest thing about the Facebook deal is that Oculus will have hundreds of millions of dollars to develop the hardware they dream of, not the hardware they have to settle for."

I didn't realize this was public knowledge, yet you certainly state it as if it was obvious. Do you have evidence of them having to settle for lame hardware that $75M of investment couldn't get them? Where did this news surface? Sounds interesting.

I don't get what point you're refuting here. Why did you start this off "No, no, and triple no. Wake up call here." That seems like a really drastic response to saying "billionaires aren't like the rest of us" — which seems to be a fairly accurate statement, no? (unless everyone here are billionaire$).

So I'm guessing you were referring to maybe a different aspect of his post?

As someone who has done plenty of indie game development, I understand their gripes, but also I know this is the "Game" we're playing here — anyone who makes any form of success should expect to be cloned. Period. So think about that from the get-go and come to peace with it in your strategy/set expectations accordingly. The second I put any app out there I assume it's out in the general "mindspace" and will probably manifest somewhere in another form at some point or another. The speed at which it manifests usually correlates to the popularity of the idea.

(Assuming you make $90k/year)

10x annual revenue I think flies by many investors books and wouldn't seem "outlandish". If need be you could probably meet somewhere in-between 5 and 10x. 2x seems like too low of a multiple.

>>>" Who you work for rarely changes who you are as a person if you already know who you are"

Quite true.

>>> " I think people fear Facebook owning it as scary because they know it will go somewhere with that much behind it rather than it not happening."

I don't really understand this sentence. Also, to be clear, I don't fear Facebook owning anything (to me that seems pointless), I was just more surprised by Carmack's/Abrash's choice —but of course its only surprising when you don't know the details that occurred leading up to it, and the real thing that made their decision. Perhaps there was an offer they couldn't refuse, and so they jumped on it. People make it sound like Oculus wouldn't have continued without Facebook though, which seems odd to me.

>> "Just now they have funding and lots of momentum."

This is the point I don't get. I hear this echo'd by everyone, but correct me if I'm wrong, didn't they raise some $75M+? So is the point everyone is making that to properly do VR, we need more than that ? Did they not have enough resources before?

(I don't know the answer to this, just curious)

Perhaps. Are there any figures released on how much Sony has spent on it? It might help us give some context to the scale of the "VR problem", and how much it costs to really go to market with a product.

I think it's awesome Carmack and Abrash are working together again. I read "Masters of Doom" back in the day, and it totally rocked my mind and took me back to a time when I was too young to realize just how impactful Carmack was on the industry that I enjoyed as a kid.

I just wouldn't have predicted that their comeback to the limelight would be working for Facebook. In my eyes, they were "bigger" than that (obviously not monetarily). They "meant" more to me. This is all subjective stuff I realize, and yes I've heard a zillion times "how good it is for VR", but it kind of indirectly gives a message that the best thing a genius who is already capable of changing the world can do is work for Facebook instead of do their own thing.

Call me a softy, but something just warms my heart when I see smart people stand out on their own, unswayed by the massive "power monoliths" surrounding them, and STILL kick ass. That's what Facebook did! And that was awesome! I just hope that spirit of entrepreneurship doesn't fade, and that geniuses know their power lies within themselves — not in deep pockets of any company.

Congrats to all involved though — I can only imagine what kind of crazy office days are ahead. The sequel to "Masters of Doom" is yet to be written.

Hey Walker, great post. I remember you starting this while at Brown, and I also remember when FishCo was shut down. I did NOT know someone used a Pokémon card for an ID. Totally believe it though :)

Inspiring story, and I'll be in touch.

Now I see what pg was talking about comment moderation. C'mon guys. Let's class it up.

There's a lot that would need to be done. I don't think the answer is just "oh tell companies to hire more minorities/older people/{insertGroupHere}". Something needs to be done to change the perception of intelligence & ability in our country/world, and it probably starts on the individual/family-level. From the time we're born, we have these images crammed down our throats "people who look like this do this", and then many of us subconsciously internalize this and treat this as "the norm". We set our own expectations (internally), and then this gets reflected out externally.

I can only speak from my own perspective as black male in his 20s (so not the age problem described in the article), but it was the fact that I was raised to NOT buy into & instead be critical of stereotypes of "what black males are supposed to do" that I even allowed myself to believe that I could start learning C++ — when I was 10 years old.

Had I spent most of my time watching/INTERNALIZING what's on BET, the news, TV, I would probably feel like there's no chance for me in tech, and I wouldn't even consider it as a possibility — therefore never apply for the job, or apply to college for a CS degree, or subconsciously set myself up for failure.

Mind programming has subtle, but POWERFUL impact on the young developing mind. I'm realizing this all later and all I can say is "holy shit, I'm grateful. Thank you, parents. Bullet dodged."

Damn, that is true. If he gets fired, then what does THAT say?

Interesting. He compares FB buying Oculus to Google buying YouTube. I see his point, but I don't quite agree with the comparison. A search engine company buying a what is ultimately a VIDEO search engine makes total sense.

The rest of his argument focuses on how we should be happy they have all the cash they need now, but then also mentions they raised over $90M prior to that.

Was $90M not enough to build it out themselves? Or did the VCs just want to flip this one quick?

>>>"to survive the inevitable mainstream enlightenment"

Well said! It dawned on me yesterday that we are in the Middle Ages of technologies. Hear me out — what I mean by this is we are in a point in human civilization where a LOT of people use technology, the Internet, computers, computer software...

...and MOST of those people have No.Clue.What.It.Is.

This to me sounds like when the Church dominated people's lives, making everyone live by a book called "The Bible".....

....that only a few monks in their "lofty ivory towers" knew how to read, and everyone else to get it from them.

They (the clergy) were the ones who had the power/privilege to disseminate and translate "the word of God" for the rest, and most people had to just....believe them.

....until the Englightenment

Warren Buffet runs an office with about 24 people, managing over $182B in revenue, $480B+ in assets, and filing 900+ page tax return annually. That is efficiency beyond anything I've seen anyone do, period.

Mark Z is certainly leveraging his position and wealth, but I wouldn't call him a Buffet yet.

I had no clue about Eich's opinions, or the opinions of Mozillans, but it's nice to know these employees feel safe enough to share their opinion and not get fired.

So true. It's fairly common for people to spend most of their lives expecting others to give them value. "If I get into Stanford/YC, then I'll be successful"

It's weird people don't think about the other way around:

• Strive for success — period — and then Stanford/YC will want YOU.

At the end of the day it's about creating value. It's not made out of thin air. It's not made from a diploma. It's not made from an acceptance letter.

It's made by You.

(hopefully)

• Does YC fund "lifestyle businesses"?

• Even a lifestyle business needs growth — just enough to support the owner's lifestyle — but growth nonetheless (unless one customer is all you ever need)

>>"Why do these smart, quantitatively trained engineers, who could help cure cancer or fix healthcare.gov, want to work for a sexting app?"

These are the questions.

Maybe its the money? Engineers see investors throwing millions at sexting apps, yet not as much "sexiness" around curing cancer (which in the long run is a LOT more sexy, IMO).

It is weird though. All these smart ass kids you go to school with, and then they're like

"We're starting a startup"

"Cool, what does it do?"

"It's a photo sharing app that allows you to share photos and meet people with similar interests."

(YAWN!)

Or maybe it's a laziness factor. Why solve the worlds big problems when you could solve #FirstWorldProblems and get paid pronto?

It's a self-perpetuating problem though, because in the long run its probably gonna bite our tech-hipster generation in the ass.

Maybe it's lack of foresight:

What happens when we're older? When we're not as "cool"? When we don't look as good in skinny jeans?

Or, even worse, what about when we've been diagnosed with cancer/something else? Wouldn't we wish that we and our nerdy peers spent time solving those problems to help save ourselves? When do we realize that while vanity, voyeurism, and sex can easily bring in the eyeballs/cash, that these things are fleeting....

...but love, health, and helping those less fortunate than us is what might actually save us in the long term.

But not too many seem to care.

It's weird.

(Back to working on my SnapChat-meets Tinder-meets Secret-meets Facebook clone. )

Anyone tried this out?

I've seen this happen as well. As a black male CEO of a VC-funded startup, I've also seen it happen to me in a slightly different way. I gotta hype up the nerdiness, the glasses, and casually name-drop my college degree just to help those around me not embarrass themselves by assuming "I'm not the guy writing the code". Unfortunately, I'm quite used to this though and rarely think to share this experience with anyone because this has been My Whole Life.

Only creepy if you make it, bro. It's not what you do, it's how you do it. Talking is a pretty basic form of communication.

Another win for #firstWorldProblem apps. Hell, you could argue that Secret doesn't even solve any problems, and probably creates more.

But damn, that stylish hipster UI and all these cool Silicon Valley cats talking about how they hate Dave Morin....who doesn't want to ride that gravy train?

"unless we do it, he doesn't want to get involved anymore." >>> From first-hand experience, this is the warning sign. Does this sound like the start of a good relationship to you? Are you ready to ride this out for years?