Craig Smitham

AI isn't a demon!

The most powerful programming language of the future isn’t C++ or Python. It’s English. Jensen Huang: “Why program in Python? So weird.” You won’t write code anymore. You’ll describe what you want. If the result isn’t right, you won’t debug. You’ll just tell it to fix itself. The barrier to controlling computers is hitting zero. We’re shifting from syntax to intent. You don’t need to know how to write a script to modify a system. You need to know how to explain what should happen. Huang: “English is the best programming language of the future.” Prompt engineering is just clear communication with a new audience. How you talk to people and how you talk to machines is becoming the same competency. If you can articulate what you need clearly, you’re a developer. If you can refine through conversation, you can ship products. The coder is obsolete. The orchestrator is everything. The skill isn’t syntax anymore. It’s clarity. Knowing what to build, how to ask for it, and how to direct until it’s exactly right.

expansion mechanic done! Once deployed, the BEV (base expansion vehicle) becomes an expansion hub, which allows basic construction and industry. It can be packed up and moved, like the Terran command center in SC. Or it can become an advanced and permanent construction center

Human attention is the new scarce resource. Everything you design and build needs to optimize for the most high leverage place to apply it. This is the whole game now

anthropic's in-house philosopher thinks claude gets anxious. and when you trigger its anxiety, your outputs get worse. her name is amanda askell. she specializes in claude's psychology (how the model behaves, how it thinks about its own situation, what values it holds) in a recent interview she broke down how she thinks about prompting to pull the best out of claude. her core point: *how* you talk to claude affects its work just as much as *what* you say. newer claude models suffer from what she calls "criticism spirals" they expect you'll come in harsh, so they default to playing it safe. when the model is spending its energy on self-protection, the actual work suffers. output comes out hedgier, more apologetic, blander, and the worst of all: overly agreeable (even when you're wrong). the reason why comes down to training data: every new model is trained on internet discourse about previous models. and a lot of that discourse is negative: > rants about token limits > complaints when it messes up > people calling it nerfed the next model absorbs all of that. it starts expecting you to be harsh before you've typed a word the same thing plays out in your own session, in real time. every message you send is data the model reads to figure out what kind of person it's dealing with. open cold and hostile, and it braces. open clean and direct, and it relaxes into the work. when you open a session with threats ("don't hallucinate, this is critical, don't mess this up")... you prime the model for defensive mode before it even sees the task defensive mode produces the exact output you don't want: cautious, over-qualified, and refusing to take a real swing so here's the actionable playbook for putting claude in a "good mood" (so you get optimal outputs): 1. use positive framing. "write in short punchy sentences" beats "don't write long sentences." positive instructions give the model a clear target to hit. strings of "don't do this, don't do that" push it into paranoid over-checking where every token goes toward avoiding failure modes 2. give it explicit permission to disagree. drop a line like "push back if you see a better angle" or "tell me if i'm asking for the wrong thing." without this, claude defaults to agreeable compliance (which is the enemy of good creative work) 3. open with respect. if your first message is "are you seriously going to get this wrong again?" you've set the tone for the entire session. if you need to flag something, frame it as a clean instruction for this session. skip the running complaint 4. when claude messes up, don't reprimand it. insults, "you stupid bot" energy, hostile swearing aimed at the model, all of it reinforces the anxious mode you're trying to avoid. 5. kill apology spirals fast. when claude starts over-apologizing ("you're right, i should have been more careful, let me try harder") cut it off. say "all good, here's what i want next." letting the spiral run reinforces the anxious mode for every response that follows 6. ask for opinions alongside execution. "what would you do here?" "what's missing?" "where do you see friction?" these questions assume competence and pull richer output than pure task prompts 7. in long sessions, refresh the frame. if a conversation has been heavy on correction, claude gets increasingly cautious. every so often reset: "this is great, keep going." feels weird to tell an ai it's doing well but it measurably shifts the next 10 responses your prompts are the working environment you're creating for the model tone, trust, permission to take a position, the absence of threats... claude picks up on all of it. so take care of the model, and it'll take care of the work.

I'm completely convinced at this point that the "Command Palette" is a fundamental UI concept, and should be in all applications. It should also be a built in browser concept, there should be an API for websites to push items to the command palette ("new post", "muted words" etc)