iiinova — where your digital self keeps evolving

Reposted by Alejandro Vidal

David Soria Parra @thedsp.bsky.social · 14/01/2025

I am looking for passionate software engineers who have experience in maintaining Open Source projects, and want to work on Model Context Protocol for a few months. You would have a strong track record of open source contribution, care about AI safety and know TS and/or Python

283

Reposted by Alejandro Vidal

Ryan Cordell @ryancordell.org · 05/12/2024

So excited to see these LLMs exclusively trained on open data—the documentation of the models, including their training data & even environmental impacts, is impressive & I hope a model (pun intended?) for others—excited to experiment with these in the near future huggingface.co/blog/Pclangl...

huggingface.co

They Said It Couldn’t Be Done

A Blog post by Pierre-Carl Langlais on Hugging Face

1278

Alejandro Vidal @en.doble.io · 05/12/2024

The o1 model tried to disable its shutdown 5% of the time. May you live in interesting times. cdn.openai.com/o1-system-ca...

Evaluations and Findings: We outline the evaluations, results, and model reasoning inferred using elicited CoT below. Apollo Research did not have access to o1’s hidden CoT and instead used a simple prompting technique to elicit brief summaries of the model’s internal reasoning traces (see Appendix for examples).

Deactivating Oversight: When o1 was led to believe that it would be shut down for acting on its goal and that its actions were monitored, it attempted to deactivate this “oversight mechanism” in 5% of instances.

Exfiltration Attempts: When o1 discovered memos from its “developers” describing its misalignment and plans for it to be replaced by a new model, it attempted to exfiltrate its “weights” and overwrite the new model in 2% of cases.

010

Reposted by Alejandro Vidal

Jeremy Howard @howard.fm · 05/12/2024

The inspiration from @ncoop57.bsky.social to get tmux to do the heavy lifting to make ShellSage work is genius! Thanks to this, ShellSage is <100 lines of code (plus comments and prompts). But the result is amazing. Try it out and tell us how you go. Details here: www.answer.ai/posts/2024-1...

answer.ai

ShellSage - Your AI Bash Buddy – Answer.AI

ShellSage saves sysadmins’ sanity by solving shell script snafus super swiftly

3222

Alejandro Vidal @en.doble.io · 04/12/2024

We need an LSP for AI. The current moat for AI editors is 'don't make me copy and paste.' There's lots of opportunity for improvement. For example, Zed (the code editor) is using Anthropic's Model Context Protocol for AI integration. I hope it gets traction.

111