"Nordhaus co-wrote the standard economics textbook taught globally"
Which is tragic because it is a neoclassical fiction book misleading millions of students. Anyone who is really interested in the history of economic thought will avoid that book for anything other than being a reference of the theoretical position of the neoclassical synthesis.
This is entirely wrong. It is crucial to teach students the foundations of the academic discipline they're about to study, which is currently the neoclassical Keynesian synthesis.
Every economic model is fiction to some degree, what matters is the usefulness of the models to make policy decisions or predict outcomes. One can branch off into heterodox schools of thought like Austrian, Marxism, Chicago, or Behavioral... but students need to be grounded in the field's consensus to be able to know how to speak intelligibly across these areas if they're to have any effectiveness.
Funnily enough when you iterated heterodox schools you didn't even mention the Post-Keynesian school which is obviously the most serious one of any of those and also the one that should be the mainstream because it models the whole economy.
"what matters is the usefulness of the models to make policy decisions or predict outcomes"
Correct and the equilibrium models used by the mainstream fail to do that in every possible way which is no wonder because the economy is a complex system that is never in equilibrium (non-equilibrium is basically the defining feature of our economy). Failing to describe the economy as a complex system failing to explain how the monetary system works are unforgivable errors and shouldn't be tought to studends for anything but showing them how fallacious thinking can lead us astray. The neoclassical Keynesian synthesis is one big fallacy of composition, it should never have gotten so much traction and the only reason it dominates is that it is politically useful to a few people on top. But it definitely doesn't model the economy in a useful way.
Weird that is exactly the theme in Ted Lasso Season 4 Episode 7 but the article seems to have been released February 27, 2026 while the Ted Lasso Episode was released September 16, 2026. Who's original idea was this?
> Unix philosophy in the system prompt could be useful if the code wants to be worked on later again
There is no system prompt that can prevent this. If all you needed was some kind of rather short instruction we'd already have that baked into harnesses a long time ago. The problem is not that agents do not have the right instructions, they theoretically have everything there is to know about software architecture already in their training data.
They do have "everything" but that's too much, I think. They need to have direct instruction that is in the context, that is appropriate for the project and codebase at hand. In the whole universe of training data, there's every approach imaginable. What's needed is enough guidance to identify the right approach consistently.
I recognize that crafting a 'perfect' prompt is impossible, but neither is writing the perfect code, or even the 'perfect' code style guide. But it is 100% the kind of problem that can be iteratively improved to a point where it's much better than what you get by one-shotting everything without much consideration of these details.
I myself am maybe 5% sophisticated if 0 is I just discovered LLMs today, and 100 is the most skilled at using AI the world has seen. What I've learned so far is that I have a lot of room to improve.
Which is why I am actually not completely worried about the careers of current software engineers: If you brought in a bunch of non-engineers to prompt Claude to build and maintain an ERP system, or a social networking site, or an ad exchange, or even Shopify clone, I don't see those products being competitive with ones where engineers armed with the same LLMs are building them.
> They need to have direct instruction that is in the context, that is appropriate for the project and codebase at hand
> I recognize that crafting a 'perfect' prompt is impossible, but neither is writing the perfect code, or even the 'perfect' code style guide
This is not about "perfect code" or style guides. For code styles we have linters, that does not require any instructions. I'm talking about software architecture for large complex web applications that dozens of people (that also change frequently) contribute to and that is spread across many different repos/services and an environment with constantly changing business requirements.
The terms that are relevant here are: coupling, cohesion, vertical slices, module boundaries and so on. This is software architecture and coding agents are terrible at this and there is no prompt and no instruction fixes this that could reasonably fit into a context window. I don't even think that coding agents fail because the lack the instructions and therefore adding instructions won't fix these failure modes.
> Studies have shown that the vape smoke stimulates the vagus nerve which causes changes in the cardiovascular system that could likely cause heart disease
Can you name this study? Are you talking about "E-cigarettes and their lone constituents induce cardiac arrhythmia and conduction defects in mice"? This study did not find what you claim. All it found is that in mice the heart rhythm during and right after exposure increased. This is far from claiming that it "could likely cause heart disease" in humans. Also human switching studies point the other way. smokers who move to vaping show improvements in blood vessel function within weeks. I don't know why people really need to twist study results to depict vaping more harmful than it is. Yes, it is not healthy and you shouldn't do it. But all scientific evidence conclusively points to vaping, even heavy vaping, still being way less harmful than smoking because we already know that basically all harm comes from inhaling the residues of combustion, not from the nicotine. Condeming vaping as being equally bad as smoking is irresponsible and unscientific and prevents proven harm reduction for heavy smokers.
> Condeming vaping as being equally bad as smoking is irresponsible and unscientific and prevents proven harm reduction for heavy smokers.
I never said this did I.
Also you’re talking about smokers moving to vaping, whereas at the moment plenty of people are going straight to vaping due to people over arguing how harmless it is compared to smoking.
As far as I know the academic consensus is that taking in more nicotine, even a lot more, doesn't turn vaping into something as harmful as smoking. Addiction is the main established "harm". Nicotine, even very much of it, is not considered a carcinogen. There are studies that suggest it could promote tumour growth but it hasn't been shown in humans. There is also decades of data from nicotine replacement therapy and Swedish snus users and it shows little to no increase in heart attacks or strokes in otherwise healthy people. Another risk is accute poisoning, i.e. swallowing large quantities of liquid by children. As far as I know even the more alarming voices regarding nicotine do not regard it as harmful as inhaling fumes from combustion.
Also I don't think that there are many people that overdose nicotine regularily because it causes nausea and dizziness so people are normally self-regulating the nicotine dose automatically. So the scenario you are proposing doesn't seem to be something we can actually observe as a common consumption pattern.
Too much nicotine is far closer to drinking too much coffee than to smoking and has similar acute effects which is why almost nobody does it on a regular basis.
> It is generally harder to build a crypto system than to break one
It was harder to design Symmetric Encryption using e.g. AES-256 than to break it? As far as I know it's design is pretty straight-forward but there is no known way to break it even with all compute of the planet at your disposal (excluding trivial ways like exposing the key).
Yes, it was. An attack only needs to work one way, but an encryption standard must resist all attacks.
There are many examples of would be crypto algorithms that died on the vine because an attack was found. It is often recommended for beginners to study breaking cryptographic algorithms long before they attempt to create them.
It didn't take 25 years to come up with Symmetric Encryption and AES but even though people try extensively to break it for the last 25 years no-one has come even close to anything that is not brute force (which is practically impossible even assuming very generous computing resources). So at least in that case coming up with the encryption seems to be a very solvable problem but breaking it seems close to impossible.
It’s worth considering AES is the result of many decades of development of prior block cipher algorithms. It is no so hard to make a variant of AES that looks similar but is not secure.
Time estimations by LLMs are hilariously incorrect all the time. It estimates very simple things that a human could do in an hour to take days or weeks and other things that are genuinely tedious and time-consuming it estimates taking a few hours. LLMs have no understanding of time and no world model that even allows them to make correct time estimates. They will always fail to provide decent time estimates unless the task is well-known, in the training data and they can extrapolate that with a simple math script.
My favourite story is of an elderly coworker with no AI experience who innocuously asked GPT-5-mini (at the time his framework's default model) to translate a 50 page engineering spec, and it kept him at arm's length for about a week about how that task would take just another 24-36 hours more. He kept asking like, you finished yet? and it just made up excuses, "so sorry, I got distracted, give me one more day", and he went "please finish, I need this", and 5-mini came back "I totally understand -- let me get to work immediately, I'll report back ASAP", end of conversation. He got annoyed but never even suspected anything wrong, because this is the kind of conversation he's used to. I wonder how long this would have continued, if I hadn't intervened by chance.
Without the published conversation, train-of-thought and intermediate output and knowing what Astra did this is nothing but unfounded claims. In the end this could have been a web search, downloading an existing enigma simulator and trying out some rather obvious things. Also what does "resisted resolution" even mean? Have there even been serious attempts to decipher the message? How serious?
Also: Why should we assume Terra, GLM or any other less SOTA and less expensive model wouldn't have been able to do the same?
> Why do you think this uncracked code was so simple to solve?
I never said this. All I said is we don't have the conversation and therefore we can't determine how easy or hard of a problem it was.
> And it's very possible Terra or GLM could crack it, turn off their web access and try yourself.
I'm questioning why this should be labeled "Astra" breaking anything implying it required "the best" model to do it when in fact any other half-decent model might have been able to do this as well.
EDIT: Okay seems like the actual prompt is published, just not on the same article that was linked. Maybe I'll give it a try.
this! a semantic class name that is scoped to only that component and only ever used in that component is pointless indirection only needed to be able the reference the actual css properties in that other file sitting next to your component by using some name.
Which is tragic because it is a neoclassical fiction book misleading millions of students. Anyone who is really interested in the history of economic thought will avoid that book for anything other than being a reference of the theoretical position of the neoclassical synthesis.
reply