Well, everyone seems to get excited about the ai thing these days, so I thought I would create an ai links page. Kind of like my old ones. I will start putting pro and con articles and models here. Personally I have found ai useful for: translation, removing noise from microphones, occasional scripting help, poetry, ocr, and thats about it.
| Link | Description | Rating |
|---|---|---|
| lmstudio | EASY way to get into ai | 5 |
| granite model | IBM provided model which allows for commercial use. | ? |
| UNSAFE llama3 model | Its face book's somewhat unsafe (It told me how to make sarin gas!) | 3 |
| somewhat safer mistral model | Seems to not let you make sarin gas. Kind of moralistic. | 4 |
| web archives with ai article | VERY interesting article on using web archives and training models on specific datasets. | 5 |
| Granite Model | IBM's granite model, suitable for commercial use | ? |
| red flag | evaluates the safety of software using ai models locally | 4 |
| fuzzy dedupe paper | uses ai to dedupe documents | 4 |
| ai models collapse | ai models collapse if they use non-human generated base data | 5 |
| llm2sh | converts plain spoken things into shell commands | 4 |
| microagent | automates tests based upon criterion | 4 |
| change | lets you autmatically do copilot like chatting locally with ollama and various local models | 5 |
| run llm locally | everything that this person has learned about running local llms | 5 |
| project mantis | project mantis hack back at the ai hacker | 4 |
| llm from scratch | helps you train and do an llm from scratch with cuda and c++ | ? |
| LLM locally | A bit expensive, but interesting how to do llm locally | 4 |
| tuskira | an automated threat feed that uses ai | 4 |
| modernbert | a encoder only model very fast | 5 |
| UNSAFE llama model | Basicically a completely polly-anna removed LLM | 5 |
| chatgpt Temporal model break | Basically a way that they broke chatgpt by using fake time travel | 5 |
| deepseek original pdf | Has the original pdf with deepseek's models etc. | 4 |
| ramalama | models in containers to make them safer | 5 |
| exo | lets you run models on distributed computes with lots of gpu's slow but lets you run bigger models more cheaply | 4 |
| voice cloner register article | nice article on how to clone voice, needs nvidia alas with a bit of vram (16gb or so1) | 3 |