alicealexandra.com
she/her • developer exerience, builder.io • writes, paints, composes, codes at alicealexandra.com • am generally, myself, a leaky abstraction
96 posts
78 followers
173 following
Regular Contributor
Active Commenter
comment in response to
post
ugh stop posting such relevant content
comment in response to
post
You can teach any agent to fish, but wouldn't you rather it know who to call to get fish on demand?
This is what Google's new A2A protocol promises: your agent gets a list of contacts for when the questions get too tough.
www.builder.io/blog/a2a-pro...
comment in response to
post
Yep. I’d rather a hastily thrown together diagram than some six-fingered action figures.
comment in response to
post
This is dedication. 😁
comment in response to
post
Teach the model once, and then let it work.
In other words: fine-tuning.
- 50 great examples > 5k-token prompt.
- Tone of voice and tool calls get baked right into the model weights.
- Adapters make this possible for all. No second mortgage for GPUs.
www.builder.io/blog/fine-t...
comment in response to
post
You'll notice the difference pretty quickly.
You get far better results from a coworker who you've taken time to onboard.
comment in response to
post
Use that document in the next chat. Keep building it over time.
Eventually, create different documents for different areas in your career and life.
You can mix and match context with every chat.
comment in response to
post
Start small.
The next time you have a successful chat with AI, ask it to make a short document about what it learned from you that enabled it to do its job well.
comment in response to
post
The main way to combat all this is through getting good at documentation.
It's a skill people spend years learning, so be patient with yourself, and seek guidance from folks who are already great at docs for us humans.
comment in response to
post
What's worse is that most of the AI tools we use today are "stateless." Every interaction is a completely blank canvas for the AI.
Even though we may feel like we've been building a working relationship with the machine, it has no idea who we are or what we do.
comment in response to
post
When we tell AI to do something for us, we provide shockingly little context and just expect it to read our minds.
We don't anticipate how unique-to-us our tasks actually are.
comment in response to
post
I love this.
comment in response to
post
26? they're not out here trying to date older women 😬
comment in response to
post
not the likes and reposts echoing the name 🙈
just needed to drop 11 days ago, and the whole world would have collapsed into coincidence.
but anyway, congrats on the launch!! gonna ruin the numbers now.
comment in response to
post
this is essentially how my favorite poems work, and i'm obsessed with trying to emulate it in my writing.
when you can summon a word that means/doesn't mean like 5 things at the same time, and then connote multiple of those meanings, it's just such a lovely chaotic space.
comment in response to
post
didn't even finish his veggies
comment in response to
post
why doesn’t this exist 🥲
comment in response to
post
This is a nice analogy!
comment in response to
post
this is the most intensely relatable thing i've seen on this platform.
but i guess everyone already knew this. 😭
comment in response to
post
Here's my advice to anyone looking to make choices matter more in their game:
Don't pit "A" against "B."
Pit all choices against time.
And for some choices, give the player interesting consequences when they don't complete them.
#videogames #gamesky #gamer
bsky.app/profile/alic...
comment in response to
post
So, this is Citizen Sleeper's power: Every single action you spend is a choice _not_ to spend it somewhere else.
What will you prioritize?
Just like real life, there aren't often wrong answers.
Only interesting consequences for you and the people you've met.
comment in response to
post
Drives aren't linear quests—they're just a list of goals you could be progressing.
But drives are often bound by time. If you don't complete one in x amount of days, the opportunity goes away forever.
You can't complete them all, and you don't always know when they'll fade.
comment in response to
post
This minimalism—I only have x amount of things I can do today—seems like it would lead to choice paralysis.
But the game overlays all your choices with meta-narratives called "drives," which is also how your character levels up to do more interesting things.
comment in response to
post
Incredible. 😇
comment in response to
post
How?
Every "day" in the game, you get 1-5 actions to go spend absolutely anywhere in the world.
Each of your actions is rolled as a dice, so it has varying amounts of power each day.
The game progresses only by you spending actions.
comment in response to
post
That said, most games have a weird sense of time.
If there's a monster pillaging a village, you can go on an 18-hour sidequest, and the village will be just fine.
What Citizen Sleeper does is make you choose what to prioritize, because it won't be there forever.
comment in response to
post
These types of games make up for that linearity by offering high degrees of interactivity in the gameplay itself.
You can be stealthy or go in guns blazing, you can pursue quests in whatever order, you can go wherever, etc.
comment in response to
post
Most games ask you to:
- Make choices in dialogue, often between a finite number of "good" and "less good" options
- Somewhat linearly go on "quests" based on those choices
comment in response to
post
That’s exactly how it works. 🤣🥲
comment in response to
post
ope nvm
comment in response to
post
3. An article about why MCP even matters, written for humans: www.builder.io/blog/model-...
comment in response to
post
2. A cloneable template repo, with lots of inline explainers: github.com/3mdistal/cs...
comment in response to
post
1. A step-by-step guide on how to build your first MCP server (without vibe coding): www.builder.io/blog/mcp-se...
comment in response to
post
AI infrastructure right now isn't very optimized, and developers are in higher demand than ever to help make it better.
So, here's what you need to know about designing good agentic systems with your existing skills.
www.builder.io/blog/design...