RandyRanderson

20 минут назадdiscuss

My claim is that this is due to alignment

позавчераdiscuss

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.

RandyRanderson

19 дней назадdiscuss

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.

RandyRanderson

19 дней назадdiscuss

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?

RandyRanderson

19 дней назадdiscuss

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.

RandyRanderson

21 день назадdiscuss

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).

RandyRanderson

23 дня назадdiscuss

Canada here: it can absolutely, definitely get worse.

RandyRanderson

27 дней назадdiscuss

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.

RandyRanderson

в прошлом месяцеdiscuss

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         │
  
  └─────────────────┴──────────────┴───────────────┴────────────────────┴──────────────────────┘

Prompt caching: −90% on input tokens (all models)

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)

RandyRanderson

2 месяца назадdiscuss

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.

RandyRanderson

2 месяца назадdiscuss

[dead]

RandyRanderson

3 месяца назадdiscuss

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

RandyRanderson

5 лет назадdiscuss

AKA the war of art[0] and I'm sure there's many, many other books in the same vein.

To dichotomize: those that show up every day anyway are likely doing something they love (even if the thing they're doing is showing up itself[1]). Those that don't likely perceive the way fwd as something they don't like. We can change that perception but it's hard.

Likely, it's best to think in a continuum of interest and that we need to move the perception or act into a realm that is self-reinforcing.

[0] https://stevenpressfield.com/books/the-war-of-art/ [1] This is an illness; a life without refuge.

RandyRanderson

6 лет назадdiscuss

This type of developer 'switch' is becoming so common that I now have to add my chrome extensions to google alerts so as to feel safe. As a user below comments: "We need to talk about how difficult it is to monetize browser extensions" b/c w/o this we will see this continue.

RandyRanderson

7 лет назадdiscuss

Please name your provider, location and url to your plan. I find your claim very hard to believe.

RandyRanderson

7 лет назадdiscuss

Canadians have slow AND more expensive Internet but are, for some reason, not frustrated. :<