But it did. What used to be unworthy of building is now totally doable. I can roll out one off ad-hoc UIs for our customer to navigate their bespoke data sets without having too much worry about expending a lot of development time to throw up a visualization page that may get discarded when its usefulness expires. So it has expanded the realm of the worthwhile if not necessarily the realm of the possible. At least not yet.
I agree. AI clearly expanded the set of things that are worth building, especially small or previously unjustifiable work. What I was trying to say is that once those things become real systems, the old constraints show up again. You still have to understand boundaries, failure modes, and how to operate what got produced.
Yes, no denying this. Now in time this will change too. I'm slowly letting Claude do some target maintenance work in AWS in non-critical environments. Over time I will let it perform reversible operations in production but that time has not come yet. And it still too often takes silly approaches to problems that have more elegant solutions. These days it has a personally of an ambitious, restless junior who wants to always get stuff done but doesn't have the depth of thought to just handle it all by itself. But the times they are a changing.
Your advice beautifully reinforces OP's case.
We now have to use auxiliary apps with more predictable behaviour because designers made such a mess of things.
This fascinates me because I tend to use Claude Code in _very_ long sessions, driving it until its context window is exhausted at which point I grab most of the session history from the terminal window and paste it right back into the context. This usually fills the context window right back up to 80-100K tokens. Seems a lot more successful especially with keeping track of recent developments than built in compaction does.
For some reason I get the best results this way. I know it's unorthodox but with my approach the agent seems to learn about the ongoing concerns as it stays 'in the loop' and I prefer it to use its minion agents to do grunt work like grepping sources or log files. That way the main context is free of monotonous blobs. I like having it act as a coding/troubleshooting companion rather than a minion to delegate short bursts of work to. I believe it's because I rarely feed it a big block of data to parse in a single prompt or let it grep incessantly in the main context that I don't get hit by the dreaded 'context rot'.
This little study seems to line up with my experiences.
However, when fed source material into the context they will lie less, right? So at this point is it not just a battle of the nines until it's called "good enough"?
I also wonder if I leave my secretary with a ream of papers and ask him for a summary how many will he actually read and understand vs skim and then bullshit? It seems like the capacity for frailty exists in both "species".
Not to mention that it would then make some hedge fund with a better backtesting harness or more AI scrutiny more successful thus keeping the financial market work as designed.
Americans, you elected someone with the mentality of a child to the highest office in your country. You should be ashamed.
Face it, this is not some recent attack of dementia as some of you claim (perhaps trying to defend your extraordinarily poor judgment). The first time I heard that man talk was in 2016 when I saw fragments of his debate with Hillary Clinton. He was as childish and incoherent then as he is now. Later, seeing some clips of his behaviour during your election campaigns it was evident that he has the language and mannerisms of a child. I suspect he stopped his mental advance around the age of early adolescence or even earlier. This is not how an adult talks or behaves.
You gave nuclear codes to a 79 year old child. I can't condemn your recklessness enough.
Because this is democracy. I didn’t want this, I didn’t vote for it. But democracy is not just electing the people you want. The last presidential election was by all accounts a free and fair election.
As terrible as the current insanity might be, this is the president the majority voted for.
It may destroy the world economy, he might commit war crimes (attacking water infrastructure might be a war crime) and crimes against humanity (tbd). Those crimes may be prosecuted following due process, but until that happens this is the president the people elected.
Condemn the people who voted for him all you want, propose rules changes to prevent it from happening again, but he was democratically elected and I can’t be ashamed of democracy.
Shame, in a democratic system, is good for exactly the same reason it is good for individuals to be able to feel it.
Every system of government has a failure mode. There are no exceptions: anarchy fails to strong men with big sticks, democracy fails to demagogues, hereditary aristocracy to literal inbreeding, dictatorships to sycophantic courtiers, etc.
A democracy that one cannot be ashamed of is simply one in which the same demagogues can keep trying as many times as it takes.
That's all fine and good as long as you keep your trash indoors. Iran is halfway around the world and the title here should make anybody feel ashamed, not just those from the country that proposes this. It's a failure of humanity, not just of democracy that we let things get this far.
The democracy in the US is faulty in many ways. Democracy isn't a black or white kind of thing, so of course you can be ashamed of the lack of democracy that ended up with this person in charge.
I'm not convinced that the last election was free and fair. There's the strange comment that Trump made about Musk fixing the election machines and all the GOP comments about fixing elections sounds to me like projection
Balderdash. Russia has elections. There are plenty of places with elected governments that don't rise to the definition of democracy. We can't really claim to be a democracy without citing the caveats that our elections are bought by the Epstein class, and that we have a nearly overt fascist movement, with some tech industry leaders in that movement, among other ways in which democracy is degraded in the US.
Not maintaining and cultivating our democracy reduces our legitimacy, and when our acts affect the whole planet, that legitimacy matters.
Him talking was broadly incoherant word salad in 2016, but I think there's a strong case to be made that his coherancy has been getting even worse over the past while.
Only having the mental age of a child and sliding into dementia are not mutually exclusive.
What you are seeing in America right now is not democracy. We have transitioned into an oligarchy that is run by a group of billionaires. The only reason we still have elections is because the elites get to select the candidates and we only get to choose between the two options they chose for us.
Most people who have significant savings in the stock market don't have the lifespan to ride out a 25 year recovery cycle. And those young enough to have the time usually don't have much in savings yet.
I guess it depends what you call "significant". I am 40 and have over 200k in my 401k, which I think is significant. And I could most likely expect to live 25 more years. If there's a crash tomorrow, my money wouldn't grow the way I am hoping it will over that time, but I should come out ok considering that I will be getting discount stocks while the market recovers.
It is significant if you remain healthy and employed with income.
But it is basically nothing if you get laid off at age 56, and you can't find another job due to age discrimination, your COBRA runs out after 18 months, but you are not 65 years old yet for Medicare . Obamacare may be completely neutered by then, so private health insurance may cost $30k/year for a 57 year-old. You still have a mortgage, you can't afford health insurance, so you take a risk and decide to skip it, because you are healthy. Then you get pancreatic cancer, and without health insurance, your chemotherapy completely depletes your 401k in one year. Then you die of cancer at age 59, because you cannot pay for the treatments anymore.
Given your government is trying very hard to relive the global demand for the US dollar and thus repatriate the trillions of dollars held outside the US that seems very unlikely.
If you're only expecting to live to 65, you would be trying to time your 401k into a roughly 5 year window (assuming you wait until 59 1/2 to begin withdrawl).
Even if tomorrow's models get good enough to complete these games we won't be able to proclaim AGI. In the realm of silly computer games alone I'm going on record saying that there are plenty of 8 bit games that AIs will trip on even when this benchmark is crushed. 2D platformers like Manic Miner or Mario need skills that none of these games appear to capture.
reply