This seems useful beyond agents.
It will save tons of traffic for scripts, text browsers, low-bandwidth connections,etc
markdown is incredibly compact and easy to parse.
The code written by AI in most cases is throwaway code to be improved/refined later.
Its likely to be large, verbose and bloated. The design of some agents
have "simplify/refactor" as final step to remedy this, but typically
your average vibe coder will be satisfied that the code just compiles/passes the minimal tests. Lines of code are easy to grow.
If you refine the AI code with iterative back-and-forth questions,
the AI can be forced to write much more compact or elegant version
in principle, but you can't apply this to most large systems without breaking something,
as AI doesn't have context of what is actually changing:
so e.g. an isolated function can be improved easily, but AI can't handle when complexity of abstraction stacks and interfacing multiple systems, typically because it confuses states
where global context is altered.
I've been working to overcome this exact problem. I believe it's fully tractable. With proper deterministic tooling, the right words in context to anchor latent space, and a pilot with the software design skills to do it themselves, AI can help the pilot write and iterate upon properly-designed code faster than typing and using a traditional IDE. And along the way, it serves as a better rubber duck (but worse than a skilled pair programmer).
the article misses log-math and log-log-math which
would use 64-bit (d)oubles are exponents in 10^d and 10^(10^d) respectively,
which allows far higher range of possible values but somewhat more
awkward math operations(addition/subtraction), though much more practical & faster to compute.
There is a point in there, long-range analysis and debugging without AI
is much harder, AI spots lots of non-obvious stuff very fast.
If we consider "spotting non-obvious flaws" a skill, this will
atrophy as beginners will learn to use AI to scan code for
flaws,it is effective but doesn't teach anything, reading long blocks
of code and mentally simulating it is a incredibly valuable skill
and it will find stuff AI misses(something that is too complex, e.g. nested/recursive control flow,async
and co-routines/threads interacting,etc), AI goes for obvious stuff first and
has to be manually pointed to "identify flaws, focusing on X".
Quntity of exercise cannot build quality.
Its self-selecting the people who can handle running and injuries
better so they adapt. The rest get injured enough to stop.
II don't think trying to "push it to using 100% of potential" is
worth any long-term health risk, especially with no long-term reward:
so you win X race/competition once and then what?
So now you're on a Wheaties box and making millions in endorsements, that's what.
Even if it shortens their life, many athletes would take a drug that guarantees athletic success: https://en.wikipedia.org/wiki/Goldman%27s_dilemma The results have been disputed, but the take-away for me is that athletes have a variety of motivations, and the perceived rewards might be very different than what you might find rewarding.
It seems to be adding tons of articles, then some of them get deleted.
I assume it's been allocated lots of compute.
The entire model is outcompeting wikipedia on quantity per topic.
If wikipedia merges/integrates some article and Grokipedia has a
specific page for it, the search engine/LLM will get that version front and center.
Grokipedia seems to have no scope limit, so wikipedia "non-notable" entries
will be SEO-optimized towards sites with the topic-names, eventually
settling on AI content farms as primary destination.
When Spain blocks CF (it does this regularly), it breaks all CF sites. Of course, the actual problem here is organised crime. Spain and Italy do this because the mafia owns them.
> When Spain blocks CF (it does this regularly), it breaks all CF sites. Of course, the actual problem here is organised crime. Spain and Italy do this because the mafia owns them.
Mafia has a vested interest in broadcast rights of football matches in Spain?
Spain blocks Cloudflare because the football league La Liga has a court order that allows them to point to IP ranges that are hosting/fronting live streams of football matches, and get ISPs to block access to those ranges.
If the sports league is influential enough to have a standing court order to be able to unilaterally block IP ranges for the entire country, I'd imagine that organized crime might take an interest. I have no idea if it's the case but when something already seems to have an outsized influence it wouldn't be crazy to imagine that others interested in that power would also take an interest.
Moreover, I think the point of the parent comment is that they're blocking quite a bit more than just football games. It sounds like the claim is that the blocking is willfully broad because of other influences, not necessarily the the purported more narrow intent is necessarily from those influences.
More than mafia, ex-francoists oligarchs. And these could be stomped down tomorrow from CF by cancelling all the tangent services for those, even for Spanish banks and related industries (tourist and construction avoiding both attacks and serious disbalancing harms). The Ibex 35 would near collapse overnight and Tebas being kicked out from their own people.
reply