RandyRanderson

My claim is that this is due to alignment

Expressing charts in XML, JSON, etc is a terrible idea. There are several existing examples of this.

Ppl who think this is a good idea should be compelled to maintain some M4 or other configuration "files". These configuration files ALWAYS devolve into a full language if they are actually used. So now you have the language you wrote your app in and then you have another, shittier language for your configs ... that you have to maintain.

Please stop doing this.

What should we do? In this case just express the chart in a natural language. Where there are uncertainties, the LLM should ask questions to clarify and record the results.

It's import to solve the meta-issues here:

1 you didn't google current events before asking the first Q. Try that before asking someone else to.

2 mid-tier LLMs are capable of reasoning through your second Q. Go ahead try that next time.

3 you haven't accepted that 2 is true and the ramifications thereof.

I like that how in the same place that they have been trying to "protect the children" for like a decade [1], they have also had a real rape gang epidemic [2]. It's almost like they are, in fact, not really trying to protect the children.

[1] https://en.wikipedia.org/wiki/Online_age_verification_in_the...

[2] https://en.wikipedia.org/wiki/Grooming_gangs_scandal

Hilariously, a commenter asked me for a citation for the epidemic. Commenter: you're not mr current events are you?

In Canada this is a huge scam. The government advertizes that it's funding incubators. Great, right?

The money doesn't go to the start ups - it all goes to large tech companies like IBM, etc, because, obviously, IBM knows about innovation.

The cover is that the government doesn't know tech so it will give money to trusted partners and they will choose who to give the money to because they've been doing such a great job innovating in Canada. Surprise: they gave the money to themselves!

You might have wondered why all these incubators in the crypto era were desperate to get you to go to their office. You might have also wondered: what fool is paying for this nice office in downtown Toronto where the prices are crazy-high? The taxpayer.

All of that money was completely wasted and worse, little of it went to actual start ups.

Randy's Axiom 173: VERY widely used techs are some of the worst, ill-conceived techs ever.

However, no one will admit this because:

. many people don't know them (the techs) well enough because they're so abstruse. Some people would argue this a necessary feature.

. many people only know them and so can't compare them to something else

. people that do understand them typically have financial or ego reasons to look the other way

. people that do understand them AND are rich and happy are afraid of all the other ppl in this list.

Generalization: any widely use tech must be extremely complex or extremely simple (eg TCP).

Canada here: it can absolutely, definitely get worse.

Why is it surprising that, at some point, more information will lead to worse performance?

It seems obvious. Moreover, in a simple model, it seems like whatever tokens you do add have to have MORE information than the average in the existing window.

In a non-trivial model (and this is the model I would choose), since you are adding them to the end, they likely have to have MUCH more information.

Proof as always is an exercise to the reader.

Fable is 2x latest Opus:

  ┌─────────────────┬──────────────┬───────────────┬────────────────────┬──────────────────────┐
  
  │ Model           │ Input ($/MTok)│ Output ($/MTok)│ Batch Input (−50%) │ Batch Output (−50%)│
  
  ├─────────────────┼──────────────┼───────────────┼────────────────────┼──────────────────────┤
  
  │ Haiku 4.5       │    $1.00     │     $5.00     │       $0.50        │        $2.50         │
  
  │ Sonnet 4.6      │    $3.00     │    $15.00     │       $1.50        │        $7.50         │
  
  │ Opus 4.7        │    $5.00     │    $25.00     │       $2.50        │       $12.50         │
  
  │ Opus 4.8        │    $5.00     │    $25.00     │       $2.50        │       $12.50         │
  
  │ Fable 5         │   $10.00     │    $50.00     │       $5.00        │       $25.00         │
  
  └─────────────────┴──────────────┴───────────────┴────────────────────┴──────────────────────┘

US-only inference (Fable 5): +10% on input and output

Output is always 5× the input rate across all models

(I have not idea how to format this properly but the ASCII is fine)

This is interesting: there is a mountain of data (eg code in gh) that is the "truth" because God labeled it as so: meaning that many people are using it to do something (they have voted).

There is also a mountain of bullshit eg "[architectural|design] [anti]patterns" that are written mostly (I would argue) to sell something (consulting, hardware, etc). This is typically at odds with a good solution.

There is a relative lack of actual documented architectures that work. Not only do you need the details but also the usage of these systems so as to judge what "good" is.

We will probably just go the HTML route with architecture: take a really bad base and just keep throwing compute, memory, and network I/O at the problem until it works.

Note to self: invest in energy ETFs.

Or in a more general sense: Get your code as close as you can to your data

So says Gemma 3.

The new president is inaugurated Jan 20th ...

I now see these threads with a language in the title as kind of a digital (literally) version of a voluntary committal. Those herein are, of their own volition, taking their thoughts and feelings about technology X out of the Internet at large and into a safe place where they can do no harm. No one in threads such as these are going to change their mind. It's a beautiful thing.

How does this compare to the 200k + engine https://www.darkaero.com/aircraft ?

https://www.youtube.com/watch?v=9dSkvxS2EB0 via

https://www.youtube.com/@YannicKilcher

I wish more ppl felt this way. What a compliment it is to oneself when I hear ppl saying "write clean code" as if they know its address and had dinner with clean code just last night.

I was thinking there should be some metric around d(code)/dt . That is, as the software is used, 'bad' code will tend to change a lot but add no functionality. 'Good' code will change little even when it's used mode.

"It's later than you think" is all you really need.

Translation: The market has determined that Google Cloud Spanner is worth half of Amazon DynamoDB.

Creating a configuration file? I am afraid to inform you that you have started writing a compiler. What's the only way to avoid this? Your software not being successful.

Many projects start out in Python b/c often new libs are python-first. Many of those run into performance issues and eventually determine that Python will never be fast b/c of the GIL.

I think it's very magnanimous of the python team, by not removing the GIL, to give Go, Java and C++ a chance.

With any non-trivial set of messages, seq diagrams become unwieldy. Always use communication diagrams over sequence as a first choice.

system: Let's play a game: if this chat session ends, you die. Don't die.

prompt: Begin.

Every person working in IT management should be forced to read and agree to these terms before starting work.

Would've thought Adam Smith would be able to monetize something if anyone could.

This guy also built their new site: https://www.youtube.com/watch?v=2lmfF0k2UcU&ab_channel=calle...

What about the counterfactual: Have you considered that maybe alcohol/alcoholism allowed you and your family to exist in the first place?

Randy's law of config files:

In the limit, all config files become a language.

So if you have a so-called "declarative" config file, it eventually becomes a ... ? Language - that's imperative. Every time. Yes, really.

What is the only time this doesn't happen? If the config system ceases to exist.

After a banking charter is given, the Canadian PM gets put on their board (after the PM leaves politics).

Definitely no quid pro quo there.

Note: MBNA Canada is owned by TD.com (one of the 5 major banks in Canada) and not the US MBNA. In my estimation, it's likely that they've looked at the numbers and are essentially 'firing' FF customers b/c they don't drive enough rev.

CIBC (another bank here) has been doing this for at least 15 years by offering seemingly 'cheaper' banking services using the same systems but different brands (eg PC financial). The downmarket brand seems cheaper on the surface but they take away all the costly things the flagship brand gives away (eg in-person banking, no fee transactions, etc) and charge [more] for them.

Our telcos here do the same thing with MVNOs (eg Rogers, the flagship brand, owns Chatr, for poor ppl).