iiinova — where your digital self keeps evolving

Marcin Junczys-Dowmunt (Marian NMT) @marian-nmt.bsky.social · 28/01/2025

Hi, the Microsoft Translator research team is looking for an intern for the summer. If you a PhD student in Machine Translation, Natural Language Processing, or related, check it out: aka.ms/mtintern

aka.ms

Search Jobs | Microsoft Careers

054

Reposted by Marcin Junczys-Dowmunt (Marian NMT)

Clem Delangue 🤗 @clem.hf.co · 16/12/2024

Just 10 days after o1's public debut, we’re thrilled to unveil the open-source version of the technique behind its success: scaling test-time compute By giving models more "time to think," Llama 1B outperforms Llama 8B in math—beating a model 8x its size. The full recipe is open-source!

48319

Marcin Junczys-Dowmunt (Marian NMT) @marian-nmt.bsky.social · 16/12/2024

Rant: Apparently every vector-based sentence alignment tool insists on having an unusable file-based API.

000

Reposted by Marcin Junczys-Dowmunt (Marian NMT)

porcoesphino.bsky.social @porcoesphino.bsky.social · 14/12/2024

It's messier, but I think this one slaps the point home a bit stronger by adding the giant squid footage. I think unique weather, like lighting sprites, would make the point just as well.

Chart of time vs:
- number of cameras (exponentially increasing ),
- giant squid footage (exponentially increasing ),
- bigfoot footage (small and not increasing), and
- good quality UFO footage (small and not increasing)

2903

Reposted by Marcin Junczys-Dowmunt (Marian NMT)

Yoav Goldberg @yoavgo.bsky.social · 13/12/2024

the anthropomorphizing in this LLM scheming paper is through the roof and the interpretations are wild, but still a cute set of experiments and a fun skim, showing some interesting behaviors. arxiv.org/abs/2412.04984

arxiv.org

Frontier Models are Capable of In-context Scheming

Frontier models are increasingly trained and deployed as autonomous agent. One safety concern is that AI agents might covertly pursue misaligned goals, hiding their true capabilities and objectives - ...

4373

Reposted by Marcin Junczys-Dowmunt (Marian NMT)

Artidoro Pagnoni @artidoro.bsky.social · 13/12/2024

🚀 Introducing the Byte Latent Transformer (BLT) – A LLM architecture that scales better than Llama 3 using patches instead of tokens 🤯 Paper 📄 dl.fbaipublicfiles.com/blt/BLT__Pat... Code 🛠️ github.com/facebookrese...

56015