Today I did some comparisons of GPT-5.1-Codex-Max (on high) in the Codex CLI versus Gemini 3 Pro in the Gemini CLI.
- As a general observation, Gemini is less easy to work with as a collaborator. If I ask the same question to both models, Codex will answer the question. Gemini will read some intention behind the question, write code to implement the intention, and only then answer the question. In one case, it took me five rounds of repeatedly rewriting my prompt in various ways before I could get it to not code but just answer the question.
- Subjectively, it seemed to me that the code that Gemini wrote was more similar to code that I, as a senior-level developer, would have written than what I have been used to from recent iterations of GPT-5.1. The code seemed more readable-by-default and not merely technically correct. I was happy to see this.
- Gemini seems to have a tendency to put its "internal dialogue" into comments. For example, "// Here we will do X because of reason Y. Wait, the plan calls for Z instead. Ok, we'll do Z.". Very annoying.
I did two concrete head-to-head comparisons where both models had the same code and the same prompt.
First, both models were told to take a high-level overview of some new functionality that we needed and were told to create a detailed plan for implementing it. Both models' plans were then reviewed by me and also by both models (in fresh conversations). All three of us agreed that Codex's plan was better. In particular, Codex was better at being more comprehensive and at understanding how to integrate the new functionality more naturally into the existing code.
Then (in fresh conversations), both models were told to implement that plan. Afterwards, again, all three of us compared the resulting solutions. And, again, all three of us agreed that Codex's implementation was better.
Notably, Gemini (1) hallucinated database column names, (2) ignored parts of the functionality that the plan called for, and (3) did not produce code that was integrated as well with the existing codebase. In its favor, it did produce a better version of a particular finance-related calculation function than Codex did.
Overall, Codex was the clear winner today. Hallucinations and ignored requirements are big problems that are very annoying to deal with when they happen. Additionally, Gemini's tendencies to include odd comments and to jump past the discussion phase of projects both make it more frustrating to work with, at this stage.
Ok, so this post is a joke of some kind (there was no 1989 version of Blue Prince).
But it raises an interesting question: would it have been possible to implement that upside down floppy disk puzzle in a game?
1. Was it even possible to insert floppy disks upside down? I lived through the floppy disk era in my childhood, but I have to admit I can't remember if the drives would even let you do this.
2. If the answer to #1 is yes, would there be any way of programmatically detecting the floppy-disk-was-inserted-the-wrong-way state?
If anyone knows of a steelman version of the "AGI is not possible" argument, I would be curious to read it. I also have trouble understanding what goes into that point of view.
In their paper, they explain that "in the case of math problems with deterministic results, the model is required to provide the final answer in a specified format (e.g., within a box), enabling reliable rule-based verification of correctness. Similarly, for LeetCode problems, a compiler can be
used to generate feedback based on predefined test cases."
Basically, they have an external source-of-truth that verifies whether the model's answers are correct or not.
When I was raising my first child, I discovered a strange, apparently innate instinct which presumably is related to the mirror neurons:
At some point the child gets old enough that you start to feed them 'baby food' on a spoon. The child isn't used to eating off of a spoon so for many weeks the process is messy. The initial challenge is getting them to open their mouth wide enough for the spoon to enter. And telling them 'open your mouth' is not particularly useful since they don't understand English at that age.
Instead, the following instinct kicks in: as you approach their mouth with the spoon, your own mouth opens. They see your mouth open and then open theirs. The crazy part is that your own mouth opening happens involuntarily at the moment you want their mouth to open. It is physically difficult to suppress it, even if you try.
I've also noticed the reverse. When the child gets a little older, they at some point want you to open your mouth, because they want to feed you something or they are curious about the inside of your mouth (this is a phase they go through). They seem to also involuntarily open their mouth wide when they want you to open yours.
> Unfortunately that 'Friedman rule' belief relies upon there being a fixed amount of money and a one-to-one relationship between money and stuff.
I'm not sure what you mean by this. The Friedman rule does not assume there is a fixed amount of money -- the rule itself recommends in some circumstances that the central bank should increase the supply of money.
> Having said that paying interest on sovereign debt is, effectively, a basic income for people who have money. Getting rid of it is a tax on rich people with savings.
A zero nominal interest rate, while possible, generally requires the central bank to implement a policy of deflation (see [1]). For example, in the US, the long term real interest rate on US treasury securities is 1.74%, so setting the nominal interest rate to 0% would require a deflation at a rate of (1.0174)^-1 per year (~1.71%). While this would eliminate some of the interest earned by "people who have money" it also has the counterbalancing effect of increasing the real value of the money which those people have saved, due to the deflation.
You may be interested in reading about the history of the quantity theory of money, particularly the disputes about it in the 19th century.
In particular, the British "Banking School" was opposed to the quantity theory of the "Currency School". The Banking School claimed that inflation was cost driven, that interest rates were one of the costs of doing business, so that raising rates would increase costs which would increase prices.
While superficially reasonable, this argument was destroyed Wicksell [1] who provided a more careful economic model which made it clear that rate-driven cost-push inflation was not at all plausible as a sustained cause of inflation.
That seems to, again, say that Erdogan believes high interest rates are forbidden under Islamic law; but that is different than saying that the Quran says high interest rates cause inflation (as the parent claimed Erdogan believed).
To be clear, I don't hold the position that Erdogan doesn't believe high interest rates cause inflation -- I don't know what he believes. I am just trying to find a source that backs up the parents' claim, if there is one.
> In Zimbabwe, which has followed the World Bank and IMF process, interest rates are 200% and inflation back at 280%.
> There comes a point when we have to accept that interest rates don't really have that much power to control inflation in the real world. It's a religious devotion to a theoretical model.
I don't understand how Zimbabwe's experience is a refutation of the 'theoretical model'.
The model says that having nominal interest rates lower than the rate of inflation increases demand for loans, which increases the money supply, which increases inflation. If Zimbabwe's interest rate is 200% while inflation is 280%, then the model says inflation should continue to increase. Which is what it is doing.
Does Erdogan believe that the Quran says inflation is caused by high interest rates? That would be fascinating if true.
However, the article you cited does not make that claim. It merely says that Erdogan is opposed to high interest rates because they are considered "usury" and are thus forbidden. This is different from saying that high interest rates cause inflation.
Do you have a different source specifically for the claim that the some people think Quran indicates that high interest rates cause inflation?