The main advantage of skills is defining a process that is at least vaguely consistent across different executions for a given task, and plugging in some of the common pitfalls an LLM might fall into for some of those executions.
But to me, both the process and the pitfalls are going to be heavily specific to the individual or team, and to the work they are doing... It's something that evolves over time as you bump into repeated rough edges.
Taking someone else's skills and blindly applying them to my situation feels odd. I don't know what rough edges those skills were made to address, so I have no reason to believe they would fit my specific needs, initially, any better than the baseline LLM.
The one thing I appreciated about my Computer Engineering undergrad - and it took me a few years to fully appreciate it - is that yes, we did cover those levels.
The first two years were shared with Electrical Engineering. The second two years started to specialize towards Computer Engineering topics.
* Physics and chemistry.
* Circuits.
* Transistors.
* Logic gates.
* FPGAs.
* Assembly.
* Compilers.
* CPU and hardware design.
* Operating systems.
* Networking layers.
* Programming languages.
* Computer graphics.
Did I master all of the above - absolutely not. I loved some of them, struggled with others. Generally the cut-off for how my brain works is logic gates, I was never strong at the levels below that.
But we did cover them, and I could honestly say I had at least a rough understanding and mental map of everything that happens inside a computer from the point where it's plugged into an outlet, to the point where pixels show up on the screen.
Genuinely curious - in your case, where do the requirements for what needs to be built come from?
In every project I've touched, business requirements are always the bottleneck - so I've never been able to wrap my head around what kind of requirements can be fed into a setup like this at high enough volume to justify it.
>Does the game actually communicate this naturally during play? Not really. The player is simply thrown into a brutally hostile world and left to suffer. In reality, players hunt these monsters to buy gear or level up, not out of melancholy.
It's more nuanced than that, and "in Dark Souls, every monster is inherently hostile toward you" is not true.
Most games have a clear division between hostile mobs you kill for XP and loot, and story NPCs which you cannot / are not supposed to attack.
That line doesn't really exist in Dark Souls. Most (all?) story NPCs can be killed, which has specific consequences if the player chooses to do so. And there are monsters throughout the game world that are functionally identical to hostile monsters - they look the same, drop the same resources if you attack and kill them - but are simply not hostile to you and are just minding their own business.
It IS more subtle than in other games, and might not even be obvious to the player at first. This gradual realization was actually one of my favorite parts of playing Dark Souls.
But there are definitely intentional gameplay elements that support this, it is not strictly text lore.
This is almost 1:1 with a project we worked on several years ago. Unfortunately it never launched - founder ran out of money. It was one of my favourite projects we’ve done and I genuinely believed in the concept, so I was sad we couldn’t see it come to fruition. But glad someone else is giving it another go!
Without giving away anything confidential, I can say your cold start plan is very similar. Can’t say it’s a good or bad plan because we never saw it executed in practice… but it’s not unreasonable!
I think distribution and stickiness will be a challenge. Even if you get enough content that users will have a great first experience, most people don’t travel that often, so getting them to come back regularly won’t be easy.
This feels particularly egregious because of our unspoken assumption that Adobe, of all companies, should have "excellence in design" somewhere on its list of core guiding principles (I know, I know, hear me out). It feels like there should be someone internally at some point who says "hold on, this really goes against who we are as a company, what happened here".
It's instructive to look at how a company presents itself to the public, so I went looking at what Adobe says about itself, and what is the first instance I can find of a principle or value that this bad UX violates.
Google result:
> Adobe: Creative, marketing and document management solutions
> Adobe is changing the world through digital experiences. We help our customers create, deliver and optimize content and applications.
About page:
>Changing the world through personalized digital experiences.
>Adobe empowers everyone, everywhere to imagine, create, and bring any digital experience to life. From creators and students to small businesses, global enterprises, and nonprofit organizations — customers choose Adobe products to ideate, collaborate, be more productive, drive business growth, and build remarkable experiences.
>Creative Cloud
>Industry-leading photography, design, illustration, and video apps that professionals rely on to do their best work.
>Creativity is not only what we enable for the world but it’s also core to the fabric of the company. It has driven our curiosity to look around the corner to transform the industry and ourselves. Over 40 years, we launched the desktop publishing revolution with PostScript, innovated and led every category that we are in — creativity, documents, customer experience management — to serve a wider customer universe. Create the future is all about being the customer and being relentless across all the elements that make up customer centricity to delight them, deliver unparalleled value and innovate to address unmet (and possibly unknown) needs.
>Raise the bar is about continuous evolution and never being satisfied with the status quo. It’s about never settling for good enough and always striving to be first, only and best. It’s about being intellectually honest and direct in talking about the things that aren’t going well and always looking to do better. At the end of the day, our ultimate measure of success is the customer and today more than ever, we need to surprise and delight them at every turn.
So really, the closest I could find to guiding principles being broken are tangential concepts like "remarkable experiences", "customer centricity", and "surprise and delight". Good goals for any company, but not especially design focused in my opinion.
Paraphrasing, Adobe as a company thinks of itself as a provider of technology to fuel content, marketing, and advertising money-making machines. Design at this point is incidental to who their customer happens to be.
I am sure individual employees might feel different, but as a company, we have no more reason to expect excellent UX from Adobe than, for example, Oracle or Salesforce.
Subscription fatigue is real, especially since most SAAS providers got a lot more aggressive with raising prices in the past few years.
Add enshittification, products randomly getting acquired and shut down, etc, and $50/month quickly stops looking like $50/month.
Not saying the math works out for the “build your own” version… But it’s not that clean for the subscription option either.
On a separate note, there is the concept of “ideal customer profile”. If the people you’re speaking with feel they can solve this problem on their own, then they are not it!
>How, the novice may ask, does one discover which version is the correct one for oneself?
>There is nothing else to it – you must eat a few hundred bowls of phở and find out. If this requires moving to Hanoi, so be it.
Not the worst life plan, to be honest!
A little bit sad that my own "death bed pho" - chicken pho from that one stall near the market in old quarter - gets just a passing mention as the only acceptable variation to traditional beef pho.
This also brings back memories of our "mystery pho man" - who had three tiny stools and one large pot outside his house every morning, looked like a character straight out of an 80's movie, and was usually sold out by 8am.
Vietnamese food has got significantly better in Toronto in the past 5-10 years - but still haven't found anything that comes even close to Hanoi chicken pho.
I have a lot of respect for Steve Blank, but my heuristic by now is to ignore any breathless posts that state “teams are doing X with AI, if you are not doing the same you’re behind”.
The much more useful posts are “my team and I are doing X with AI”. Of course, the challenge there is that the ones who are truly getting a competitive edge through AI are usually going to be too busy building to blog about it.
>For me, I've always called it the "school at night" phenomenon.
It's funny, I've always loved that kind of environment. Quiet high school hallways after everyone's left, empty university buildings late at night, offices after hours, even empty offices that haven't been moved into yet. For me it evokes feelings associated more with watching a rainy day from inside, or lofi-girl with headphones studying.
I understand why it can evoke horror or unsettling feelings for people, but for me the first word that comes to mind is just "peaceful".
Even the environments in the Backrooms trailer - minus the obvious horror elements - look like they would be a lot of fun to explore!
The past failure is in the abstract, and in the past. And anyway, they were unfairly maligned. There is an inside version of the story that they will be happy to tell you, which was clearly not their fault.
But that is neither here nor there. What is important is the now, and in the now you are in the presence of someone who is Good At Making Money. And you too, by joining forces, will be Making Lots Of Money with this charismatic person, who can clearly achieve great things and will be clearly avoiding any past missteps that may have caused their downfall right before reaching greatness (but weren’t their fault anyway).
I joke that I'm on the "Claude Code workout plan" now.
Standing desk, while it's working I do a couple squats or pushups or just wander around the house to stretch my legs. Much more enjoyable than sitting at my desk, hands on keyboard, all day long. And taking my eyes off the screen also makes it easier to think about the next thing.
Moving around does help, but even so, the mental fatigue is real!
Ironically, this brings us one step closer to believing the simulation hypothesis might be true... In which case, maybe there is no real world anyway ;)
But to me, both the process and the pitfalls are going to be heavily specific to the individual or team, and to the work they are doing... It's something that evolves over time as you bump into repeated rough edges.
Taking someone else's skills and blindly applying them to my situation feels odd. I don't know what rough edges those skills were made to address, so I have no reason to believe they would fit my specific needs, initially, any better than the baseline LLM.