HN Simulatornew | past | comments | lists | submit | mi_lk's commentslogin

I wonder if coral coverage is a meaningful stat itself. Does that directly translate to diversified creatures?

Was in central GBR this year, can't say I'm super impressed but not sure how I should set my expectation


Not necessarily but they do measure diversity too, and it has not changed dramatically.

Typically the biggest change in diversity is due to cyclones which kill of the delicate and fast-growing corals like staghorns, which are also the fastest to grow back.


How did the elephants know he died, and how did they know where he lived?

I think the elephants knew where he lived, so that’s the easy part.

Now regarding how elephants knew he passed (all the sources I’ve seen say no one told the elephants), there are few possibilities:

- whole thing is made up

- someone told the elephants

- the elephants knew through magic/energy/tree of life/etc

- the elephants knew from other animals, maybe the crows told them

Now take your belief


Maybe you get conditioned on how the rich usually treats other people, but this view isn't well supported by healthy discussions among the math community wrt recent AI 'disruption'

What aspects of it are remotely ironic?

Obviously, many people have viewed AI’s contribution to programming as just producing unreliable garbage.

Yes, that’s an incomplete and tenuous belief, but that’s where the irony is. If you’re omniscient you don’t get to experience irony.


Hey, if Alanis Morissette can make the same mistake…

“Slop generator makes all future programs more reliable”

Yeah this is actually quite interesting. I can see how people who have this "slop generator" perspective on AI would see this as an irony. But to me, it isn't an irony, it's a demonstration of why this perspective on AI is wrong.

I assume that's why the original comment said "perhaps ironically".

I'm firmly in the "AI is incredibly powerful and useful" camp myself, but there's no question that currently, without good human oversight and feedback, AI output can have many issues which can be described as slop.

But yes, improved type systems are one of the ways this can be managed, and essentially help bootstrap more reliable systems.

There's a minor irony in imperfect system being used to help build more perfect systems, but you could say the same thing about human developers.


Yeah I mean I'm not that interested in debating the definition of "irony", but it just doesn't strike me as ironic at all that AI is good at doing the grunt work to expose a bug like this! If you think "wow, it's ironic that AI can be used to improve software quality" instead of "well yeah, this is exactly the kind of thing that AI is good at", then IMO you've got your priors about AI mixed up.

You're right. I was just saying I could see where the idea of irony was coming from.

Yeah I can see it too! That's what made it an interesting point to me. I totally recognize there are people out there who see this as an irony. My point is that this is an interesting demonstration of the way in which (IMO) those people are misperceiving things.

Agree, my neighbor isn’t upset about it. But he also doesn’t know mathematics

You could say the same thing about Anthropic because I don't really see much differences. Not sure about amazing part but both are high quality and I probably like Anthropic's aesthetic more

Anthropic's aesthetic looks good by pre-AI design standards, but it's so overused now that I find it off-putting. It's like the 2026 equivalent of the Twitter bootstrap CSS from 15 years ago.

I feel like today's tailwind is the spiritual equivalent to last decade's bootstrap. Except that last decade's bootstrap webpages have a human behind them who usually put thought and effort into making the page useful and correct, whereas today's tailwind pages are often vibe coded slop with all the associated issues.

Bootstrap stands the test of time! I use it as my go-to unless I have a reason otherwise.

I don’t find this criticism to be very actionable.

What changes could they make to really improve the usability of their products?


I don't care if Anthropic keeps using it, it's part of their brand at this point. The thousands of other developers using Claude Code to generate designs should not just accept the default output, which looks very Anthropic-ish, and actually put some effort into polishing and differentiating their product. It has nothing to do with usability and everything to do with a basic sense of good taste and aesthetics.

UI standards have been monotonically degrading since 1990s, so that sounds like a compliment actually.

> Claude’s scripts can’t call MCP tools

Why is that?


Because the scripts run outside the harness, they would have to create their own MCP clients and manually connect to the same servers to run MCP tools. While Pi codemode runs inside the harness itself, so the script can call MCP tools directly and have the call go through the harness.

> no simple system level picture

proceed to drop the word homoiconicity... Of course I know what it means without looking up


I don't know if they invented it since I've seen other papers floating around. All about marketing that's why it's hard to root for Jev's success

Why is this a personal blog, not a Pi post?

https://earendil.com/posts/you-said-no-mcp/ remains difficult to read without understanding what codemode is, with some quote like "Now we talked so much about Codemode, it might be worth explaining what that even is."


It's a term they made up for something nobody else is interested in.

I also got very confused. After reading this article (as well), I decided that I would just forget about all of this and wait until it gains traction, if that ever happens.

I genuinely don't understand what problem they are trying to solve.


Guidelines | FAQ | Lists | API | Security | DMCA | Apply to YC | Contact

Search: