I just managed to download and safely store approximately 4,729 digitized photographic slides that my grandfather took throughout his life while traveling around the world. I roughly know the timeframe spans from the 1960s to the 2000s. Some are labeled; others are not. The chronological order is completely messed up, and it will take me a long time (especially if I have to do it alone) to parse, identify, and group all the files into collections. Meanwhile, I also want to share them immediately online under a CC BY-NC-ND 4.0 license to prevent commercial exploitation, as this project will take years and proceed in batches with pauses in between. I feel people deserve to see the world as it was in the past—from wild Australia to the deep Arctic. My plan: Submit everything to the Internet Archive without any organization first, then curate and organize directly on the IA while keeping everything public. I also realize I'm very new to this kind of digital preservation, so I'm open to hearing from y'all if you have any advice. Thanks!

Comments URL: https://news.ycombinator.com/item?id=47518716

Points: 2

# Comments: 0

Comments URL: https://news.ycombinator.com/item?id=46443724

Points: 3

# Comments: 0

It almost seems like we got inspiration from our brain to build neural networks!

I guess Ollama needs to update their version, maybe!

Thought for 1 seconds Okay, the user is asking "Who are u?" with a casual tone ("u" instead of "you", exclamation mark). Let me break this down.

First, I need to address the question itself. They want to know who I am as an AI assistant. My standard response is that I'm DeepSeek R1, designed to be helpful and handle reasoning step by step. But maybe they're not familiar with AI terms in general. The "u" part might just be their way of speaking, so I should reply politely using "you" form.

Next, considering the context. They started with an HTML tag " "

----

And it hung there without a reply. It might be an OpenWebUI bug but not so promising

Then I installed it and it was a VSCode fork.

Comments URL: https://news.ycombinator.com/item?id=44553268

Points: 1

# Comments: 0

https://garden.tcsenpai.com/bookmarks/ai/ai-convos-notes/gem...

Comments URL: https://news.ycombinator.com/item?id=42480260

Points: 1

# Comments: 0

Comments URL: https://news.ycombinator.com/item?id=42431447

Points: 1

# Comments: 0

Comments URL: https://news.ycombinator.com/item?id=41982247

Points: 3

# Comments: 0

Comments URL: https://news.ycombinator.com/item?id=41918857

Points: 2

# Comments: 0

Comments URL: https://news.ycombinator.com/item?id=41836497

Points: 41

# Comments: 48

- # Changelog

## [1.1] - 2024-03-19

### Added - New `model_tokens.json` file containing token limits for various Ollama models. - Dynamic token limit updating based on selected model in options. - Automatic loading of model-specific token limits from `model_tokens.json`. - Chunking and recursive summary for long pages - Better handling of markdown returns

### Changed - Updated `manifest.json` to include `model_tokens.json` as a web accessible resource. - Modified `options.js` to handle dynamic token limit updates: - Added `loadModelTokens()` function to fetch model token data. - Added `updateTokenLimit()` function to update token limit based on selected model. - Updated `restoreOptions()` function to incorporate dynamic token limit updating. - Added event listener for model selection changes.

### Improved - User experience in options page with automatic token limit updates. - Flexibility in handling different models and their respective token limits.

### Fixed - Potential issues with incorrect token limits for different models.