The elephant’s name? Luigi.

This is SpaceX so I assume they meant cybertruck

So you’re saying it was Space Jesus?

Right, but this is a democracy we are talking about. If half of the people participating are convinced the entire selection is no better than a random pick then that is very damning.

Maybe if you don’t choose it’s a vote for a lottery to pick. If half the population doesn’t vote then the winner is a random person. So if the authorities manage to prevent people from voting then they can’t seize the system with their own pick

Antisocial people develop an antisocial AGI promising it won’t be antisocial towards a select group. Surprised Pikachu when the AGI concludes they are not in the in group

Let’s say I agree the concept of mind is relative, would you be willing to accept a rock has a mind?

Let me restate the point differently: lowering the bar for what you consider intelligence doesn’t make the AI sound any smarter.

By defaming intelligence you aren’t making the AI sound smarter. But you are making yourself the fool.

Bingo. It can’t be the AI that’s not working, it must be the workers!

The current MAGA “Christians” are like the Pharisees of Jesus’ time. So focused on the law while trying to feel holier than others that they would condemn the savior for healing on the wrong day instead of recognizing the miracle of the healing

Well said. I often say we’re more interested in being proven right then doing actual good. The Pharisees embody that attitude.

Absolutely. It’s amazing how many articles showcasing vibe coding is just people reinventing things like a password generator.

If it gets it wrong the first time I rarely reprompt. I know I can get it to fix it, but it’s usually faster for me to do it because I already figured out where and what to do the fix. Low key think it’s just a ploy to get us to burn more tokens. Sure correcting it means it writes a few lines to the memory file, but it’s only a matter of time before it trips over that context as well.

I have similar problems whenever I send it to investigate a bug and the local runtime is inside a container. It cannot reliably translate paths without the help of an IDE. Hell, it even occasionally mangles API paths if I have it prefixed elsewhere in the codebase (despite having Claude.md etc, your context needs to be pure for it to be reliable). Having it fix a Dockerfile is comically bad.

Any luck with integrating platform.io? Have a esp32 project but VSCode can’t provide type hinting with it’s main c++ extension that is used by platform.io.

Everything listed should be done before ever getting into code along with business and product partners.

Ehh, it really depends on where the risk is and the problem is LLMs can’t evaluate for that unless you feed it everything. Some projects need code experiments before you settle on an architecture, but that’s only if you’re a pioneer (which frankly is where the money is at).

In my experience there are three ways to be successful with this tool:

• write something that already exists so it doesn’t need to think
• do all the thinking for it upfront (hello waterfall development)
• work in very small iterations that doesn’t require any leaps of logic. Don’t reprompt when it gets something wrong, instead reshape the code so it can only get it right

The issue with debugging is that it doesn’t actually think. LLMs pattern match to a chain of thought based on signals, not reasoning. For it to debug you need good signals in your code that explicitly tell what it is doing and the LLMs do not write code with that level of observability by default.

Edit: one of my workflows that I had success with is as follows:

• write a gherkin feature file describing desired functionality, maybe have the LLM create multiple scenarios after I defined one to copy from
• tell the LLM to write tests using those feature files, does an okay job but needs help making tests run in parallel.
• if the feature is simple, ask the LLM to make a plan and review it
• if the feature is complex then stub out the implementation in code and add TODOs, then direct the LLM to plan. Giving explicit goals in the code itself reduces token consumption and yield better plans

Maybe 1% of them are winning

Fuck that. Saying empires are inevitable is a lot like saying fascism is inevitable. Maybe it’s true but you shouldn’t identify with the thing and make it’s purpose your own

You make it sound like democracy is a linear phenomena. There are likely tradeoffs

What I find interesting is how we abstract away the actual work needed to keep either scenario running reflects how billionaires justify their own extremes. The heat death being a most extreme example as there is no “spare” energy for other organism to be conscious. The uploaded consciousness is detached from reality, living in a dieing universe, and still insists it has a right to exist at the cost of new venues of consciousness.