f38zf5vdt
Born on December 04, 2019•1335 Karma
People who are experiencing unrest and idleness are easy to recruit -- and if you hang out with people ages of 18-30, you'll see there's no shortage of them.
1. By giving this name a pattern, people can have higher level conversations about it.
2. There is a small amount of new software here. Claude Code and https://claude.ai/ both now scan their skills/ folders on startup and extract a short piece of metadata about each skill from the YAML at the top of those markdown files. They then know that if the user e.g. says they want to create a PDF they should "cat skills/pdf/skill.md" first before proceeding with the task.
3. This is a new standard for distributing skills, which are sometimes just a markdown file but can also be a folder with a markdown file and one or more additional scripts or reference documents. The example skills here should help illustrate that: https://github.com/anthropics/skills/tree/main/document-skil... and https://github.com/anthropics/skills/tree/main/artifacts-bui...
I think the pattern itself is really neat, because it's an acknowledgement that a great way to give an LLM system additional "skills" is to describe them in a markdown file packaged alongside some relevant scripts.
It's also pleasantly vendor-neutral: other tools like Codex CLI can use these skills already (just tell them to go read skills/pdfs/skill.md and follow those instructions) and I expect they may well add formal support in the future, if this takes off as I expect it will.
> But yes, thanks: I was once offered this challenge when faced with a Ren’Py problem, so I grit my teeth and posed my question to some LLM. It confidently listed several related formatting tags that would solve my problem. One teeny tiny issue: those tags did not and had never existed. Just about anything might be plausible! It can just generate Whatever! I cannot stress enough that this is worse than useless to me.
The probabilistic machine generated a probabilistic answer. Unable to figure out a use for the probabilistic machine in two tries, I threw it into the garbage.
Unfortunately, humans are also probabilistic machines. Despite speaking English for nearly a lifetime, errors are constantly produced by my finger-based output streams. So I'm okay talking to the machine that might be wrong in addition to the human that might be wrong.
> It feels like the same attitude that happened with Bitcoin, the same smug nose-wrinkling contempt. Bitcoin is the future. It’ll replace the dollar by 2020. You’re gonna be left behind. Enjoy being poor.
I mean, you were left behind. I was left behind. I am not enjoying being poor. Most of us were left behind. If we invested in Bitcoin like it was the future in 2011 we'd all be surfing around on yachts right now given the current valuation.
Every other intellectual job will presumably be gone by then too. Maybe AI will be the second great equalizer, after death.
One can argue all day about timelines, but AI has progressed from being fully inexistent to a level rivaling and surpassing quite some humans in quite some things in less than 100 years. Arguably, all the evidence we have points to AI being able to take over AI research at some point in the near future.
Does it?
That's like looking at a bicycle or car and saying "all the evidence points out we'll be able to do interstellar travel in the future".
Incorrect. The difference between interstellar travel and land based travel on earth is enormous. The difference between current AI and AGI is tiny in comparison.
You're not saying it, but people might interpret 'interstellar travel' to be faster than light or very close to it, which means breaking the laws of physics or spending prohibitive amounts of energy. AGI needs no such thing, as evidenced by human brains running on < 100 watt.
Interstellar travel at far lower speeds is indeed probably something we will be able to do, looking at what we've done in space travel in the past 100 years. Although again, the resources required to do so as dictated by the laws of physics make it incredibly expensive. Given the low benefit it is probably not going to happen soon.
Reaching AGI is cheap as fuck and far more potent in comparison, so it will happen sooner.
Splendid. You should probably tell people like Yann LeCun this. He will be happy to hear it. /s
> Interstellar travel at far lower speeds is indeed probably something we will be able to do
Speed is not even an issue. We don't even know bigger problems like the long term effects of zero gravity in the human body or what dangers we'd encounter beyond the heliosphere.
Do you have an actual counterpoint or is this edgy nonsense the extent of your capabilities?
> We don't even know bigger problems like the long term effects of zero gravity in the human body or what dangers we'd encounter beyond the heliosphere.
So you agree that your analogy was bad. Good.
I don't really think this is true, unless you'd be willing to say calculators are smarter than humans (or else you're a misanthrope who would do well to actually talk to other people).
Even the chatgpt voice mode is an okay conversation partner, and that's v1 of s2s
variance is still very high, but there is every indication that it will get better
will it surpass cutting edge researchers soon? I don't think in the next 2 years, but in the next 10 I don't feel confident one way or the other
The various 'deep research' tools available today can do this. You can't. AI already surpasses you (and me) in this task. Now think about the result after asking less intellectually capable people to do this.
Before you start balking about "hallucinations", pick some country you know about and ask a similar question to Google Gemini (2.5 Flash, and enable 'Deep Research'). Check the results and reconsider your 'calculator' straw man and 'misanthrope' ad hominem.
>Check the results and reconsider your 'calculator' straw man and 'misanthrope' ad hominem.
How is the calculator a strawman? What is the argument that I am attributing to you that you do not hold?
As for the ad-hominem: I'm glad you don't dispute your misanthropy.
I said: "AI has progressed from being fully inexistent to a level rivaling and surpassing quite some humans in quite some things in less than 100 years"
You attacked the intentionally inane (which is the purpose of a straw man): "Calculators are better at all humans in arithmetic, so they are smarter than all humans"
In no way is what I said close to what you attacked.
> As for the ad-hominem: I'm glad you don't dispute your misanthropy.
Sure, double down on your fallacious nonsense instead of opening your mind to reason and engaging with my point in good faith.
I provided properly described evidence for my point. You're stuck in "AI is just some calculator on steroids". Do your 'deep research' assignment before responding.
The only thing that actually worked was knowing the target language and sitting down with multiple LLMs, going through the translation one sentence at a time with a translation memory tool wired in.
The LLMs are good, but they make lot of strange mistakes a human never would. Weird grammatical adherence to English structures, false friend mistakes that no one bilingual would make, and so on. Bizarrely many of these would not be caught between LLMs -- sometimes I would get _increasingly_ unnatural outputs instead of more natural outputs.
This is not just for English to Asian languages, even English to German or French... I shipped something to a German editor and he rewrote 50% of the lines.
LLMs are good editors and suggestors for alternatives, but I've found that if you can't actually read your target language to some degree, you're lost in the woods.
I have been astounded at the sophistication of LLM translation, and haven't encountered a single false-friend example ever. Maybe it depends a lot on which models you're using? Or it thinks you're trying to have a conversation that code-switches mid-sentence, which is a thing LLM's can do if you want?
https://www.nbcnews.com/news/us-news/group-50-people-shoplif...
Yes, in the chat where a reporter was accidentally present, many of the messages were set to be disappearing. I don't know why anyone would do that if not to avoid recordkeeping laws.
> The images of the text chain show that the messages were set to disappear in one week.
https://apnews.com/article/war-plans-hegseth-signal-chat-inv...
Further, Project 2025 suggests bypassing federal record keeping legislation by simply holding in-person meetings without record.
https://www.youtube.com/watch?v=xxe55mU4DA8
Oddly, the Project 2025 training videos that presumably the members of the executive cabinet have seen say _not_ to delete messages or set messages to auto-deleting _because_ that would be in violation of federal record keeping legislation.