mm321

it seems that only an LLM is able to explain things about this field clearly, without recourse to jargon and without recursive acronyms.

only google bard could tell me (chatgtp3.5 has a too old knowledge cutoff date). They are trying to get the capabilities of ChatGTP plugins (apparently)

>what is Langchain?

LangChain is a framework for developing applications powered by large language models (LLMs). It provides a standard interface for connecting LLMs to other sources of data, as well as for persisting state between calls of a chain/agent. LangChain also provides a collection of memory implementations, and examples of chains/agents that use memory.

Here are some of the features of LangChain:

    Data-aware: LangChain allows you to connect your LLM to other sources of data, such as databases, APIs, and file systems. This makes it possible to build applications that are more powerful and differentiated than those that simply call out to an LLM via an API.
    Agentic: LangChain allows you to build agents that use LLMs to make decisions and take actions. This makes it possible to build applications that can interact with their environment in a more sophisticated way.
    Chains: LangChain allows you to chain together multiple calls to an LLM, or to other utilities. This makes it possible to build more complex applications that can perform multiple tasks.

LangChain is a powerful tool for building applications powered by LLMs. It is easy to use and provides a wide range of features. If you are interested in building an application that uses an LLM, I encourage you to check out LangChain.

>is langchain trying to extend the LLM with plugins, similar to what is possible with ChatGtp?

Yes, LangChain is trying to extend the LLM with plugins, similar to what is possible with ChatGtp. This will allow users to add new functionality to their LLMs without having to modify the underlying code.

For example, a user could create a plugin that adds the ability to translate text, or to generate different creative text formats. This would allow the user to use their LLM for a wider range of tasks.

LangChain is still under development, but the team is working on making it easy for users to create and deploy plugins. They are also working on adding new features to the plugin ecosystem, such as the ability to share plugins and to rate plugins.

I believe that LangChain has the potential to be a powerful tool for developers who want to build applications powered by LLMs. The ability to extend the LLM with plugins will make it even more powerful and versatile.

judging by the amount of money involved: is it correct to say that we now have a space race towards AGI going on between a few big corporations? Microsoft is reported to have invested billions into OpenAI

he is asking for clemency without requesting it - i mean that's the point of quoting Matthew at the end of the letter. But I agree, this is an amazing piece of language...

not sure about that. i suspect that AGI might be a tool to help one of the bigcorps to grab power. Until now the state and the bigcorps were keeping each other in check, there was a kind of 'balance of power'. Now they might get a tool to upset this balance of power.

Whoever gets AGI first might turn into Buy-N-Large or ACME Corp, whatever... (i suspect it's all about the big price - ultimate power) - it's kind of the 'ring to rule them all' - if AGI is achievable within a realistic time frame...

* now let's see if that's the dystopian future that we are really after :-) *

now is 'AGI is just around the corner' an example of techno-optimism or techno-pessimism?

your explanation makes sense, however python doesn't allow division of floating point number by 0 either:

  >>> type(1.0)
  <class 'float'>
  >>> 1.0/0
  Traceback (most recent call last):
    File "<stdin>", line 1, in <module>
  ZeroDivisionError: float division by zero

However numpy lets you do it - it is only a warning

  >>> import numpy as np

  >>>
  >>> np.divide(1.0,0)
  __main__:1: RuntimeWarning: divide by zero encountered in    true_divide
  inf

Also: in javascript you can divide by zero

  > 1/0
  Infinity

But python throws a divide by zero error:

  >>> 1/0
  Traceback (most recent call last):
    File "<stdin>", line 1, in <module>
  ZeroDivisionError: division by zero

Still you do have infinity and nan in python - because these are part of the floating point spec.

  >>> float('inf') - float('inf')
  nan
  >>> float('inf') == float('inf')
  True
  >>> NAN=float('inf') - float('inf')
  >>> NAN == NAN
  False

However that's not mathematics, it's computers (these are even stranger...)

I have my own little programming language - PYX [1] - and i don't allow this madness (even if it is a violation of the floating point spec ;-)

  pyx
  > mathconst.Infinity - mathconst.Infinity
  Error: results in 'not a number' - that's not allowed here
  #(1) mathconst.Infinity - mathconst.Infinity
     |....................^

  > 1/0
  Error: Can't divide by zero
  #(1) 1/0
     |..^

[1] PYX - https://github.com/MoserMichael/jscriptparse - it's supposed to be an educational programming language, where I am trying to have detailed error messages, my side project.

there is a difference between infinity and not a number, NaN isn't event equal to itself, in nodejs you get:

  > Infinity + Infinity
  Infinity
  > Infinity - Infinity
  NaN
  > Infinity == Infinity
  true
  > NaN == NaN
  false

The fun thing: NaN to the power of zero (because technically the type of NaN is a ... number)

  > NaN ** 0   
  1
  > typeof(NaN)
  'number'

By the same logic, NaN is also even because

  > NaN + NaN
  NaN

but i think it's better not explain that to your six year old...

the book says there is no technological progress because the bad capitalists are living off their rents, or something like this. However we have seen some technological progress since 1916... (and the planned economies used to be stagnant)

so will it now be harder to get credit? What do the experts say?

One of the problems of the last bank run: the remaining banks were unwilling to grant any new loans - because they were afraid to take up any new risks. Is it possible that we will we see something similar?

good idea! reminds me a bit of the sunglasses of Zaphod Beeblebrox... the 'Joo Janta 200 Super-Chromatic Peril Sensitive Sunglasses' https://hitchhikers.fandom.com/wiki/Joo_Janta_200_Super-Chro...

Something optimistic:

"Skating away, skating away, skating away On the thin ice of the new day"

https://www.youtube.com/watch?v=S5D9HZyYI6g

(still it's a sad event :-( )

... i think it's the ghost of the Soviet N1 project - it's quite a challenge to have more than a dozen engines working togather; all of these engines start to responate - it's downhil from thereon...

https://www.youtube.com/watch?v=U9fkYIrRwbo

The article mentions a study which is showing that the 'Algebra for none' approach has failed - despite that official want to adopt this policy to all of California.

Does that mean that they ignore the feedback of the study, because of ... ideology?

That must be a few years back, i think they no longer serve canned spam/loof to the servicemen (and women).

system calls don't change, however glibc does deprecate and remove features, occasionally. See:

https://abi-laboratory.pro/?view=timeline&l=glibc

Correction: https://manpages.debian.org/testing/manpages-dev/syscalls.2.... is listing some system calls as removed. I didn't know that. Strange things happen at sea.

Also: things did disappear from procfs.

> The Linux system API doesn't change much

really? they added epoll, aio (they later added io_uring as a better aio), ebpf. Real threads were added with clone(2). Routing changed from ipchains to iptables. They added all the stuff needed for containers: cgroups, namespaces and what else - the Linux system API saw lots of action.

Look here: lots of additions came since Linux 2.2 https://man7.org/linux/man-pages/man2/syscalls.2.html

They even added sysfs, as procfs is now regarded as 'old and cluttered'

Also lots of changes in glibc.

it still has some real problems with nuances.

the submission should be marked as satire (that's what they put on top of the article)

never seen a pull requests with so many comments, and where the comments to the pull request read like ... twitter :-)

i have written/am working on a simplified programming language for kids. The language has it's own REPL/Shell and is more kind of text based.

https://github.com/MoserMichael/jscriptparse

i would really appreciate some some feedback on my side project

we had the Human cloning moratorium https://www.science.org/content/article/biologists-adopt-clo...

I am not an expert, does anyone know how that one worked out?

Asked ChatGPT

> Did the Human cloning moratorium work?

Yes, the Human Cloning Moratorium did work. It was initially established in 2002 and renewed in 2020 to Ban All forms of Human Reproductive Cloning as well as Research into Human Somatic Cell Nuclear Transfer. Despite certain scientific advances and proposals for legislative reforms, reproductive cloning of humans continues to be prohibited under the terms of the moratorium.

> Where there any violations?

Violations of the Human Cloning Moratorium have been reported. In 2011, Chinese Scientists claimed to have successfully cloned a human embryo, though the scientist has since denied any involvement in this experimentation. Additionally, reports have suggested that a company in the United States has been attempting to clone a human, though these reports have not been confirmed. As such, these potential instances of human cloning have not been considered violations of the moratorium.

> But you just said that the moratorium did work, isn't there a contradiction between you second and your first statement?

There is no contradiction between the two statements. While violations of the moratorium have been reported, the moratorium as a whole is still in effect and has been successful in prohibiting reproductive cloning of humans. The occasional violations of the moratorium do not indicate that the moratorium has been unsuccessful in achieving its purpose.

> So will we see a war between clones and robots?

No, there is no indication that a war between clones and robots will occur. The Human Cloning Moratorium does not place any restrictions on the development of robotics or artificial intelligence, and so the development of these technologies is not expected to lead to a conflict between the two.

Did anyone look at the case histories? Was there a second opinion on the diagnosis? Maybe big pharma trying to push even more medication may be part of the problem. Interesting that the no one is mentioning this possibility...

here is my take: interest rates are already where they used to be in 2008, that would imply that people have a hard time paying back their mortgages. Trouble with housing would imply that real trouble is somewhere around the corner.

here is a tools that is showing interest rates over several decades: https://tradingeconomics.com/united-states/interest-rate

virtual threads are still in preview. At which stage/release will they be in regular usage? (not preview) Is anyone planning to use virtual threads, at this stage?

i understand that virtual threads are very similar to goroutines in golang

that's what he is saying after the slides

  Is there another bad assumption today? 
  The recent failure of Silicon Valley Bank has raised fears        
  of a new banking crisis. One way to look at SVB's failure  
  is: SVB assumed that interest rates won't rise.

what i don't understand: how did they handle the banking crisis of the eighties? Somehow that one didn't manage to kill the economy, how?

I am not sure. I asked chatgpt yesterday to write a palindrome with two given words, it came up with complicated sentences, but these weren't no palindromes. I wonder if you won't get similar results with code.

found these videos about the plato system https://www.youtube.com/watch?v=tTmWcGhlXqA

https://www.youtube.com/watch?v=THoxsBw-UmM

also there is https://en.wikipedia.org/wiki/PLATO_(computer_system)

they mention that they were linked by a network, is it known what kind of transport protocol they were using on the CDC systems?

i things blogging and personal side projects keep my sanity. Not much, but its a big deal, for me.

> I'm curious what they're doing now.

building skynet, apparently. All powered by k8s!