Wow that's a dumb take. The whole point of ACID is that you can get roughly the same result but have a system that can serve more than 1 user at a time.
If you own the owners of media, you own all the journalists by virtue of the fact that to be a journalist requires someone to get a job as a journalist. In a place like the US you might have a handful of top people freelance and still be able to eat, but that is very rare.
You don't even need to go overseas. Just look at the NY Times and why they got the Iraq war so wrong or for even more egregious examples go and look at our wars before that. The fact that many of the high level positions on the news desk at the Times are filled by former employees of the US State department or intelligence agencies might give you a hint.
It's a herbicide, not a pesticide. I clicked the article because I was surprised that any current pesticides are that harmful to humans.
Pesticides are, generally, safe to humans. Herbicides are, generally, not at all safe to humans. Roundup is probably the most safe outside of per-emergents like corn husks or whatever, but it's not a free ride either.
> Pesticides are substances that are used to control pests. They include herbicides, insecticides, nematicides, fungicides, and many others (see table). The most common of these are herbicides, which account for approximately 50% of all pesticide use globally.[0]
You're trying to be pedantic, but you're actually wrong. If you think about it, from the perspective of anyone trying to raise crops, weeds are pests. (They are pests to lots of non-farmers, too.)
Similarly...
> A pest is any organism harmful to humans or human concerns. The term is particularly used for creatures that damage crops, livestock, and forestry or cause a nuisance to people, especially in their homes.
> Plants may be considered pests, for example, if they are invasive species or weeds.
While saying "it's an herbicide, not a pesticide" is categorically incorrect, I still think it would be better if the journalist used the more specific and less confusing term here.
I am dubious of all the claims that say something designed to kill organic life is safe because it just means "safe at X dose". Like there isn't a pesticide made where I could drink a tablespoon of it and be fine. It just doesn't present noticeable effects at tiny doses so it is labeled safe.
Like if I drank a 1/4 shot of Vodka every morning I wouldn't notice it at all, but I imagine it would have some impacts on my health over the long run.
Not to mention we might have 30+ chemicals/medications/additives/whatever all being consumed constantly at "safe levels" with no research into how they interact or accumulate.
There are many common pesticides which have extreme toxicity to humans, including HCN (Hydrogen Cyanide), (ab)used under the brand-name Zyklon B in WW2, and still sold today as a (controlled-use) pesticide under generic brand names.
It's a chasm-leap to say that pesticides are generally safe to humans.
they are designed to target specific aspects of the insects nervous systems that humans dont have and are used in small doses/by the time any residue reaches a human its diluted. herbicides are very different.
They both make stuff up and make very obvious mis-interpretations of evidence. If you take the output of an LLM, and ask another LLM to check it, this dramatically reduces this. Even if you do it with the same LLM but without the existing context. I was able to write a detailed analysis of a rule system by doing this with 3 steps, claude -> chatgpt -> gemini3. It caught all the mistakes, including overstatements and vague statements. It wasn't perfect, but even after one review the # of mistakes or stupid statements was almost 0.
"With Opus 4.5, Claude Code feels like having a god-level engineer beside you."
Well, not to me or the people I respect. It's getting very good, but it's like having a recent college grad who obsessively reads documentation. Someone with low skill but very high knowledge, often knowledge they are mixing up or not quite getting right.
I think if Claude is already 'better' at coding than you, maybe think about going back to college to be a lawyer or something. For the rest of us, lets just hope that Claude hits some natural limit before it gets better than us too. If it doesn't hit some limit I think we have a year or two.
Yet when I try it, it feels like a developer fresh out of a coding bootcamp with no real experience. There’s no real reasoning, problem solving is still brute forced. It still rewrites rather than modifies. The context is way too limiting and it gets lost in its own “thinking”
The problem solving is very very not brute force. I have seen it make detailed analysis. Often if a problem stumps me it also stumps Claude, no surprise there. But if I give it a ticket I haven't looked at yet, it is often able to find the exact problem via careful 'reasoning' and fix it in 1/100th the time it would take me.
Except I’ve coached a lot of those people and there’s usually a method to their madness. You can sit down, help them back up to where they went off the rails, and it all makes sense.
I had it One-shot the full architecture for a fairly advanced distributed system for a client. It then one shot the actual code design (following absolutely all our our internal requirements on auth, stack to use, security, code styling, documentation, etc). It then one shot (and we code reviewed everything thoroughly) each of the 5 micro services needed.
It one shot the infrastructure to use and created the terraform file to put it up anywhere. It deployed it.
It caught some of the errors it had made by itself after load-testing, and corrected them. It created the load test itself (following patterns from previews projects we had).
It did all of this in a week. With human supervision on each step, but in a fucking week. We gave it all the context it needed and one-shotted everything.
It is more than god-level. If you are not getting these increases in productivity, you are using it wrong.
Hey would you be willing to share your claude.md? I'm only starting out with AI coders, and while it often makes good choices for straightforward things, I find the token usage gets bigger and bigger as it proceeds down a list of requirements - my working hypothesis is that it's having to re-read everything as the project gets more complicated and doesn't have a concept of "this is where I go to kick it for this kind of thing".
Lol ok dude, good luck with your 'I just resell the output of Claude and I can't tell when it makes mistakes' business model. I'm sure it is a long term valid economic niche.
Now, I resell the output of AI supervised by engineers.
We can tell when it makes mistakes. It used to make a ton. Now, with the right context, it really makes very few mistakes (which it can find itself and fix itself)
I never heard of Anthony Bourdain until years after he died. I guess I wasn't the right age, I was having a family and at work all day whenever his shows took off. He seems like a genuinely interesting person, but there are so many other interesting thoughtful people that don't have relatable cooking shows and I think Anthony Bourdain, as great as he is, gets quite a bit more attention than he probably warrants. Don't take that the wrong way, he's genuinely thoughtful and interesting, but he gets a LOT of attention OVER AND OVER.
I'll throw out Tim Kreider (author of We Learn Nothing, among other books) as someone else you might find worthwhile to checkout.
I was very deficient and they gave me 50k UI per day prescription vitamin D3 for 60 days. Sure enough I was high-normal on my next test. 800ui is likely not enough to have any effect unless you consistently take it for years.
It was for 60 days. If they continued to take this much indefinitely it would surely cause troubles, but 60 days when starting from deep deficiency is reasonable.
It is high, but it's not extreme. 50k IU just once is an equivalent of about 7000 IU daily for a week, which won't really move the needle much if you're seriously deficient (in fact, it's still within what's considered a safe daily dose for healthy people - you can produce more than that from sunlight alone). You can feel free to take your "hammer" weekly, no deficiency required.
When I took >5000 IU daily for three months, I only raised 25(OH) D level in my blood from 9 to 30 ng/ml, and there's no evidence of toxicity below 150 ng/ml.
Of course, when dealing with high doses you need to keep your levels in check, as absorption can differ between individuals.
reply