Category Archives: Tech

How to run LLaMA on your local PDFs

I needed this urgently for indexing PDFs as Spotlight on the Mac is highly erratic after all this years.

Anything LLM seemed the most promising approach with an easy to use GUI and being well documented. But indexing failed after several hours, so I went on with LM Studio. Also this installation turned out to be more complicated than expected due to library “dependency hell” and version mismatch spiralling…

  1. Download and install LM Studio
  2. From inside LM Studio download your preferred model
  3. Index your PDFs in batches of 1,000 using the Python script below
  4. Combine indices and run queries against the full index

30.000 PDFs result in a 4G index while the system is unfortunately not very responsive (yet)

 

Continue reading How to run LLaMA on your local PDFs

CC-BY-NC

More AI headlines

-1-

While we are still waiting for the Nobel prize speech of Geoffrey Hinton in December, AI makes even more negative headlines.

[Hinton] “I worry that the overall consequences of this might be systems that are more intelligent than us that might eventually take control.” He also said he uses the AI chatbot ChatGPT4 for many things now but with the knowledge that it does not always get the answer right.

 

-2-

The sheer power consumption of running AI models is frightening. Nature News asks if AI’s huge energy demands will spur a nuclear renaissance

Google announced that it will buy electricity made with reactors developed by Kairos Power, based in Alameda, California. Meanwhile, Amazon is investing approximately US$500 million in the X-Energy Reactor Company, based in Rockville, Maryland, and has agreed to buy power produced by X-energy-designed reactors due to be built in Washington State.

 

-3-

A former OpenAI employee talks on his blog how AI is using copyrighted material eg stealing content.

While generative models rarely produce outputs that are substantially similar to any of their training inputs, the process of training a generative model involves making copies of copyrighted data. If these copies are unauthorized, this could potentially be considered copyright infringement, depending on whether or not the specific use of the model qualifies as “fair use”. Because fair use is determined on a case-by-case basis, no broad statement can be made about when generative AI qualifies for fair use. Instead, I’ll provide a specific analysis for ChatGPT’s use of its training data, but the same basic template will also apply for many other generative AI products.

Effects can be measured only indirectly for example by the visitor count at Stack Overflow where the traffic declined as many user (including me) don’t need Stack Overflow anymore.
Here is another phantastic discussion over at PP between Henry Leirvoll and 495yt on the very basic questions of copyright.

humans get inspired (parsing the external examples or experiences through their inner understanding and individual perspective) they start working to make something with their tools, skills, time and purpose. the result represents the author, their influences and their message.
a lot of this process is protected by copyright.
ai is not inspired. and it has no personal perspective or tools. no message to transmit.
any message put into prompts by an ai user is translated by it’s LLM layer into other, more complex prompts, which also get treated quasi-randomly by the weights and biases of the model, as well as rand seeds.

 

-4-

And well, ChatGPT can produce malicious code even with all precautions: Researchers Bypass AI Safeguards Using Hexadecimal Encoding and Emojis

If a user instructs the chatbot to write an exploit for a specified CVE, they are informed that the request violates usage policies. However, if the request was encoded in hexadecimal format, the guardrails were bypassed and ChatGPT not only wrote the exploit, but also attempted to execute it “against itself”, according to Figueroa.

CC-BY-NC

The technology of environmental damage

Here are some impressions  from my visit last week -a  reactor dome without cooling towers. and substation without function.

<irony>Thank you very much Franz Josef Strauss, Konrad Adenauer, & Max-Planck-Gesellschaft for all your efforts</irony>

https://www.fjs.de/der-politiker/aemter-funktionen/atomminister/
CC-BY-NC

The currency of the New Economy won’t be money, but attention

Time to revisit the groundbreaking 1997 @mgoldh  paper in Wired “Attention Shoppers! The currency of the New Economy won’t be money, but attention”

As is now obvious, the economies of the industrialized nations – and especially that of the US – have shifted dramatically. We’ve turned a corner toward an economy where an increasing number of workers are no longer involved directly in the production, transportation, and distribution of material goods, but instead earn their living managing or dealing with information in some form. Most call this an “information economy.”

CC-BY-NC

Ein Fahrrad Abstandswarner

Nach Stromzähler und Gasuhr kommt hier nun mein drittes Raspberry Pi Zero Projekt: ein Abstandswarner für vorbeifahrende Fahrzeuge. Das erste Mal habe ich davon in einem wissenschaftlichen Artikel gelesen, dann gab es den Radmesser in Berlin (das Projekt war toll aber die Kiste dann doch etwas sperrig).

Auch auf Kickstarter stand mal was und dann gibt es auch noch den 200€ Varia Radar von Garmin – allerdings hatte keines der bisherigen Projekte eine Kamera eingebaut.

Laser und ToF hatte es mir immer schon angetan, dann probieren wir das auch mal hier.

Continue reading Ein Fahrrad Abstandswarner

CC-BY-NC

Apropos Gasboykott – wie hoch ist eigentlich mein Gasverbrauch?

Den Gasverbrauch zu reduzieren wäre nun auch aus aktuellen politischen Gründen sinnvoll. Allerdings müsste man dafür den Verbrauch verstehen und nicht nur einmal im Jahr ablesen…

Katapult auf Twitter https://twitter.com/Katapultmagazin/status/1502327030150533125

Nachdem es mit etwas Computerkenntnissen möglich ist, einen Stromzähler mit einem Raspberry PI auszulesen, müsste die Methode auch beim Gaszähler funktionieren. Die “Gasuhr” funktioniert dabei so, dass zwei Balgen wechselseitig gefüllt werden und die Füllung einer Kammer über eine Kurbelmechanik ein Zählrad antreibt. Continue reading Apropos Gasboykott – wie hoch ist eigentlich mein Gasverbrauch?

CC-BY-NC