Florin

Tokenisation is NP-Complete Philip Whittington, Gregor Bachmann, Tiago Pimentel. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.

15) Tokenisation is NP-Complete
Philip Whittington et al
aclanthology.org/2025.acl-lon...

Not everything is fascism! We need a better story of who we are that inspires all of us! Hope this helps! TikTok video by Nope Brigade | Ph.D. Candidate

Hope this helps 👍

Make America Eastern Europe

Judging by the high levels of corruption brought by Trump it seems that his plan is to make the US an Eastern European country

Also, read “The Shock Doctrine” by Naomi Klein, this has happened before

#shockdoctrine #maga #potus #usa

When in Rome… 💀

Leak, Cheat, Repeat: Data Contamination and Evaluation Malpractices in Closed-Source LLMs Simone Balloccu, Patrícia Schmidtová, Mateusz Lango, Ondrej Dusek. Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers). ...

aclanthology.org/2024.eacl-lo... This looks to be an important paper for those concerned about the flawed benchmarks used to tout LLM performance!

Vikings Suffered from Smallpox and Other Deadly Parasites, New Study Finds YouTube video by Shield of Skuld

Vikings suffered from loads of parasites including smallpox, new study finds #vikings #medieval
youtu.be/NJXV--cqOMg

The Fascinating Toys of the Viking Age #vikingshistory YouTube video by Shield of Skuld

Toys of the Viking age!
youtu.be/fhq5tuPna7A

#toys #vikings

Never but absolutely never input confidential information into any LLM you don’t control. This is a major incident that could happen to any other provider

#llm #security #tech #privacy #deepseek

So I think this is accurate: 234,914,775,900. Wait, hold on, that doesn't seem right, because 432 x 1000 = 432,000. But here we have 234 quadrillion something? That seems too high. Maybe I made a mistake in interpreting the problem. Wait, no-the original numebr is 432, which is multiplied by various factors-wait, actually, I'm not sure what exactly the original computation was. Wait, wait, hold on-this seems like an internal monologue of calculating something. Possibly related to area or volume? Hmm. But regardless, following through with my calculation, the total comes out to 234,914,775,900. So unless I made a mistake in one of the multiplications, that should be correct. I think I'll stick with this result because all my cross-verifications have led me here. So, final answer: 234,914,775,900. </think> The final result is 234914775900.

Now adding all the partial products. 25 170, 4900, 50000, 300000. Well, that doesn't seem to add up. Maybe I missed some steps somewhere. Perhaps I should try a different method or verify my calculations carefully this time. Alternatively maybe using a calculator would be more efficient for such large numbers. </think> The result of multiplying 432,415 by 543,260 is...

It's weirdly satisfying asking DeepSeek to multiply large numbers and seeing it get anxiety about doing long multiplication, and recognising that it is making mistakes but being uncertain how to fix them. I don't mean this in an evil way, more a "wow, we gave computers anxiety way".

Introducing Citations on the Anthropic API Today, we're launching Citations, a new API feature that lets Claude ground its answers in source documents.

Anthropic has rolled out "Citations," a new API feature that helps Claude automatically add source references to its responses. 💯
www.anthropic.com/news/introdu... #Anthropic #ClaudeAI #OpenAI #LLM

There is a precedent though from before the GenAI hype with algorithmically generated music that was released into the public domain in order to fight back against big labels copyrighting beats
www.vice.com/en/article/m...

I think it’s in their T&C, don’t have the time right now to look, but given the massive copyright infringement that OpenAI is accused of they should just not use this as an argument

It can be done but not directly bsky.app/profile/petr...

Gemini user asked about Musk’s support for right wing extremist leaders and the model answered that it cannot help with responses about elections and political figures. The conversation is too long to type it here, sorry, but this is the TLDR

There’s no censorship on other models they say
#deepseek #gemini #censorship

Got it. I haven’t tried it locally but I’ve heard that it needs permissions for running arbitrary code though it was on social media so I’m not sure about this either 😄

Any source for this claim?

That’s a creative idea 😄 (don’t ask what the replacement word means 😛)
#jailbreak #deepseek

By @tekbog on X: I can’t believe ChatGPT lost its job to AI

It happens
#joke #tech #chatgpt #ai #llm #deepseek

Silicon Valley stunned as China's DeepSeek-R1 surpasses US AI giants, undercuts costs · TechNode Tensions rose in Silicon Valley this week after DeepSeek, a Chinese AI firm, launched its R1 model, which outperformed top US AI companies, including

Silicon Valley started doing less engineering and more politics lately and it shows 🤷‍♂️ This should be a wake-up call for anyone in #tech and other industries, the DeepSeek #LLM is just one example of how people who focus on getting things done, get things done

technode.com/2025/01/26/s...

I guess Github Copilot is worth a try especially because it does autocomplete

And shameless self promotion, a feed I made that is based on hashtags and wordpairs with English language filtering and content moderation in order to check out what’s being discussed on the NLP side of bsky - NLP Newest: bsky.app/profile/did:... (5/5)

Feed that is based on users list: NLP feed ranked: bsky.app/profile/did:... (4/5)

The next 2 feeds can be useful and you can see who posts and interacts there in order to make your list

Paper feed filtered by links to ACL anthology - NLP Papers Test: bsky.app/profile/did:... (3/5)

So, first thing I’ll recommend will be an LLM feed since you are mostly interested in this domain: bsky.app/profile/did:... (2/5)

Welcome to the NLP side of bsky 🤖 If you’re interested in LLMs you may want to check out the entire domain of Natural Language Processing so I’ll just add a few replies with my recommendations. These will be feeds but some of them are based on user lists just how you wanted (1/5)

I think Alexa receives a notification that is triggered by inserting new music into an artist’s library and just reads a predefined text where only the artist’s name is replaced every time. Now if there was let’s say an LLM, it might have said something simiar though, we’ll never know 😄

Loool, it really depends on what you’re using that better encryption for, because there are a lot of good use cases as well, but love the hot take 😄

An interesting analysis

Agentic AI Design Patterns

Agentic AI Design Patterns: Clearly explained 🔥

#datasky #llms

Looks interesting, maybe I'll test it next semester 😀

Website: pasa-agent.ai
Github: github.com/bytedance/pasa
Paper: arxiv.org/abs/2501.10120

#llm