Tony is a Geek

Been absent a while, have had many things to be focused on; however, this recent little nugget needed to be documented & shared, mainly because I did this on my personal laptop & I need to recreate it somewhere else and this mechanism just makes it easier - also, this might help someone else out too. Right, so what am I talking about? About a year ago I was doing some new stuff with LLMs and RAG (ingesting own documents as the data to use rather than the LLM training data) and it was okay-ish, it did the job.  Zoom forward a year and obviously things have moved on, quite a bit. The RAG tools & code have improved significantly, it still takes time to ingest though - haven't found a way to speed that part up, well, I'm focused on offline/airgapped/onpremise solutions, it could probably be faster if using a Cloud SaaS offering, but that is of no interest to me, so I'll accept the time it takes. What are the steps inolved? Get a bunch of documents, upload them to be...

I predicted a while back, maybe a year ago that the whole chatGPT LLM ( Large Language Model ) "thing" will hit it's peak around Aug '23/Sept '23 and then decline towards Dec '23/Jan '24 where people will start looking at non-pay / non-monetised usage of LLMs. I've also been a keen advocate of moving the usage / runtimes OFF of "other people's servers", ie. what you call " Cloud ", because they are incentivised to implement vendor lock-in in subtle ways such as getting you to use a service that only they offer, or store your core data in a datastore that you cannot export / lift&shift elsewhere without it costing more than it is worth, therefore stealth lock-in. I cannot really complain, businesses are in the business of business, therefore, they are driven by financial transactions and you, as the customer ( still makes me chuckle that the "IT people" call customers "end users", just like drug dealers r...

Well, the sun is out, the frost is melting, it actually snowed yesterday, it didn't snow anywhere else in the UK ( that I'm aware of ), but it did snow a LOT in California ( and still is )  Here's a photo of my garden from yesterday morning, I was very surprised as it meant I couldn't really continue with the landscape waterfall remodelling that I'd started the previous day: With such loveliness that Spring is coming and Winter is just making an attempt to show it is still a force to be reckoned with, I was pondering on how I spend my last couple of days of "freedom", ie. the as-before-mentioned-time-off.  I'll document below the tech. toys that I decided to setup & get working ready for next months "time off" where I can pull a lot of this technology together to actually start to "make something". Oh and then I noticed this headline in my fav. IT news website:  IBM announces European layoffs and for some uncontrollable reason,...

Google has literally let the genie out of the bottle: https://sites.google.com/view/genie-2024 " We introduce Genie, the first generative interactive environment trained in an unsupervised manner from unlabelled Internet videos. The model can be prompted to generate an endless variety of action-controllable virtual worlds described through text, synthetic images, photographs, and even sketches. At 11B parameters, Genie can be considered a foundation world model. It is comprised of a spatiotemporal video tokenizer, an autoregressive dynamics model, and a simple and scalable latent action model.  Genie enables users to act in the generated environments on a frame-by-frame basis despite training without any ground-truth action labels or other domain-specific requirements typically found in the world model literature. Further the resulting learned latent action space facilitates training agents to imitate behaviors from unseen videos, opening the path for training generalist agents of...