#nlp

Leshem Choshen @LChoshen@sigmoid.social

How big of a deal would it be if someone developed a language model (kind of like ChatGPT) which didn't hallucinate, didn't use prodigious amounts of electricity/water/compute/memory, which ran locally or on a distributed user mesh instead of corporate server farms, and which remembered and learned from what you say if you want it to? Something which was reliable and testable and even interpretable -- meaning you could pop the hood and see what it's really doing. Would you be inclined to use a system like this? Are there other things you'd still take issue with?

#LLM
#ChatGPT
#NLP
#NLU

**Leshem Choshen** @LChoshen@sigmoid.social · Jun 26

Jun 26

The Swedish National Archives shared 1.2m images of handwritten documents from 1600-1900+
In addition, they share a model for writing to text
Such marvelous data opportunities, kudos

https://medium.com/@linnea.karlberg.lundin/from-handwriting-to-searchable-text-usi[…]o-make-millions-of-historical-documents-accessible-3431b9c2673c

Example:
https://sok.riksarkivet.se/om-soktjansten/ai-transkriberade-arkiv

https://huggingface.co/datasets/Riksarkivet/frihetstidens_utskottshandlingar_seg

Medium · Jun 25From handwriting to searchable text: using AI to make millions of historical documents accessibleBy Linnéa Karlberg Lundin

#AI #history #swedish

**AIagent.at AI, GenAI, AGI** @ai@defcon.social · Jun 13

Jun 13

AIagent.at AI, GenAI, AGI @ai@defcon.social

»Small Purchases, Big Risks: Shadow AI Use In Government« https://www.forrester.com/blogs/small-purchases-big-risks-shadow-ai-use-in-government/ #AIagent #AI #ML #NLP #LLM #GenAI

Forrester · Jun 13Small Purchases, Big Risks: Shadow AI Use In GovernmentPowerful AI tools are now widely available, and many are free or low-cost. This makes it easier for more people to use AI, but it also means the usual safety checks by governments — like those done by central IT departments — can be skipped. As a result, the risks are spread out and harder […]

**WriterOfMinds (she)** @WriterOfMinds@sigmoid.social · Jun 10

Jun 10

WriterOfMinds (she) @WriterOfMinds@sigmoid.social

Small demo this month! I always wanted to be able to see Acuitas "thinking" and I've updated the semantic memory visualization to make that possible. https://writerofminds.blogspot.com/2025/06/acuitas-diary-85-june-2025.html

writerofminds.blogspot.comAcuitas Diary #85 (June 2025)Adventures in robotics and AI on a shoestring budget. SFF Fiction and occasional video game appreciation.

#ArtificialIntelligence #AI #chatbots

**Mark Wyner Won’t Comply** @markwyner@mas.to · Jun 10

Jun 10

Mark Wyner Won’t Comply @markwyner@mas.to

What I told Siri to say (“I hate this sap smear across our windshield”) vs what Siri said.

#VoiceRecognition #Siri #Apple

Continued thread

**Aaron** @hosford42@techhub.social · Jun 7

The only actual machine learning the system uses, aside from its purely emergent ability to learn language from context, is in the parser, where I adjust the probability of matching certain patterns based on prior success in understanding the user.

Continued thread

**Aaron** @hosford42@techhub.social · Jun 7

I wrote this code in my spare time, over about a decade. I wrote the parser, the knowledge graph, the conversational engine, everything from scratch in pure python. It starts out literally knowing nothing except English grammar, and learns everything from interactions with the user. These tests I posted... It is literally learning the words from context as I use them. It had no idea what a dog or an apple or the color red is until I tell it things about them.

Continued thread

**Aaron** @hosford42@techhub.social · Jun 7

Do you see how the system answers questions it doesn't know? That's right. It says, "I don't know." Say no to hallucinations.

Continued thread

**Aaron** @hosford42@techhub.social · Jun 7 *

Jun 7 *

Here's another passing unit test. Again, this is stuff I wrote almost a decade ago, before LLMs were even invented.

> The brown dog bites me.
> The black dog barks at me.
> The dog that bites me hates me.
> Which dog hates me?
< The brown dog.
> Does the brown dog bite me?
< Yes.
> Does the brown dog hate me?
< Yes.
> Does the black dog hate me?
< I don't know.
> Does the dog that barks at me hate me?
< I don't know.
> Is the brown dog the dog that bites me?
< Yes.

**Aaron** @hosford42@techhub.social · Jun 7

Just dug out some of my code from almost a decade ago, pre-LLM, and got it working again. Some examples of what it could do, taken from actual passing unit tests, are below. Lines starting with > are what the user says, and lines starting with < are what the system says.

> The apple is red.
> The worm is in the apple.
> The apple is in the basket.
> Where is the worm?
< In the apple.
> Where is the apple?
< In the basket.
> Is the worm in the apple?
< Yes.
> Is the apple in the basket?
< Yes.
> Is the worm in the basket?
< I don't know.
> What is in the apple?
< The worm.
> Is the apple red?
< Yes.