Why do we need long running agents? Most of my experienced value with LLMs has been like 1 to 10 turn chats. Should they just ban longer chats to solve these issues?
Because you get the biggest time-savings when you can let it run longer between each time it needs a human in the loop.
I have multi-week runs of Claude Code going to work on a compiler project. I have a week-long run of Claude Code where it is writing a real-time strategy game.
In both cases I occasionally review code, and complain a bit about things it has gotten wrong until it's back on track. In both cases it is working to specs that have produced plans that have produced TODO lists. In the latter it wrote the specs itself. In the former, the specs are externally imposed (rubyspecs test suite).
In both cases it means I get involved ranging from ever tens of minutes to every few hours, but mostly then to just confirm it can continue, with more detailed reviews every day or so.
Having to review output and give instructions every turn would drastically diminish the value.
I'm on the top Claude Max tier. Just upgraded. I could probably make do with the lower one, but I hit the limit (for the first time) on the lower Claude Max this week, and I get enough value from it that I was not about to wait for a session reset.
Protecting users in the bargains we strike with big tech is a worthwhile and noble effort, but privacy law has generally woefully failed to do this.
Millions upon millions have been spent on cookie banners -- people are still arguing about them in this thread -- but there is almost zero benefit to this expense.
The main thing that's good about this, IMO, is that fundamentally training a large language model and privacy law as it's written today cannot coexist. They are incompatible. And allowing someone to break the law forever (as is happening today) is not a good long-term solution.
> Training a large language model and privacy law as it's written today cannot coexist
If they aren't compatible, then the conclusion is abundantly obvious; the LLM has to go, not privacy. Small and questionable economic utility in exchange for a pillar of stable democratic society are NOT negotiable tradeoff.
There is enough data on the internet to train LLMs without breaking a single privacy law. If the economic value of LLMs are as real as the companies like to claim, there is enough data on the internet to train LLMs while paying for proper royalty for every single word.
I don't argue that privacy laws have been perfect. Only a fraction of GDPR seems to actually do much. But bending over backwards because big tech slips a few dollars in the pocket of Brussels is NOT the reason we should revise those laws.
One thing I loved from Osho (spiritual guru) is the notion that everyone thinks they are "extraordinary" but actually the happiest person is the person who is ordinary. Being ordinary and just eating breakfast and sleeping and doing a job is - in fact - extraordinarily rare.
The same Osho who ran an expensive cult in the 70s and 80s?
Putting that aside, it's hard for me to associate simple with happiness. That's the opposite of motivation, from my unenlightened perspective. It's hardly a rational or smart choice since not being challenged also makes one a bit narrower when it comes to seeking out new experiences. But even if you take the intellect out of it, it 'feels' wrong. And some things are challenging to achieve and bring fulfillment.
I used to really have a problem understanding why people hold peace as some ideal. It's not that i want violence, it's that if i expand on the idea of peace, I always end at "nothing". Like the idea of heaven, it's pure peace, it's… the lack of all these challenges and struggles and pains on so on. it's nothing! How does that even make sense to strive for a state of nothingness?!
This bothered me for so long until at some point, I just grew up. Peace is not nothing in the sense of null. It's nothing more in the sense of empty. I got this from some buddhist writing: emptiness is not the same as nothingness.
We are vessels and such. I found this tremendously helpful. Peace is like… space for being.
And so simple happiness, I'd say is not rudimentary, it's more like essential? The more I think on it, it's hard not to see the "core" happiness-es as quite profound. Like happy to exist. To experience each sense and such. I'd say that's quite amazing to get to that level of happiness. and we wouldn't call that "complex" happiness?
Thanks for posting. Every time I've read a RLS book lately I've been blown away by how entertaining and well done they are.
Treasure Island - pure gold. Kidnapped - gold.
I recall in the introduction to one of them he explains he wrote these stories for boys. Adventure, danger, fun characters. If you have sons you'll know there is a certain aesthetic young boy love and these books deliver it.
I also was amazed how much I enjoyed his books for adults, like the one about being on a ship as a kid (can't find the name).
If you look into his biography you find some really hard things that I guess he transformed into writing.
> If you have sons you'll know there is a certain aesthetic young boy love and these books deliver it.
Reminded me immediately of Montehomo, the Hawks Claw, chief of the ever-victorious.
> At night, when the boys had gone to bed, the girls crept to their bedroom door, and listened to what they were saying. Ah, what they discovered! The boys were planning to run away to America to dig for gold: they had everything ready for the journey, a pistol, two knives, biscuits, a burning glass to serve instead of matches, a compass, and four roubles in cash. They learned that the boys would have to walk some thousands of miles, and would have to fight tigers and savages on the road: then they would get gold and ivory, slay their enemies, become pirates, drink gin, and finally marry beautiful maidens, and make a plantation.
>LLMs and robotics look to be the first mainstream technological development in a long while which not only reduces the number of workers needed, but also doesn't have a commensurate increasing of the size of the economy in terms of increased wages through efficiency and profits being paid as wages
This article (with limited data I'll note) only talks about the first part -- that it's eliminating jobs. It doesn't say that it isn't also creating jobs.
LLMs have only been a big deal for 2 years. are you saying that all of this middle class shrinkage arrived because of that specifically? the original comment was saying this is an LLM-specific issue.
reply