@leventov.bsky.social
Reposted
Analyzing the ethics and risks of autonomous agents is crucial. Thank you for your insightful work @mmitchell.bsky.social @evijit.io @sashamtl.bsky.social @giadapistilli.com
New piece out!
We explain why Fully Autonomous Agents Should Not be Developed, breaking “AI Agent” down into its components & examining through ethical values.
With @evijit.io, @giadapistilli.com and @sashamtl.bsky.social
huggingface.co/papers/2502....
We explain why Fully Autonomous Agents Should Not be Developed, breaking “AI Agent” down into its components & examining through ethical values.
With @evijit.io, @giadapistilli.com and @sashamtl.bsky.social
huggingface.co/papers/2502....
Paper page - Fully Autonomous AI Agents Should Not be Developed
Join the discussion on this paper page
huggingface.co
February 6, 2025 at 3:58 PM
Analyzing the ethics and risks of autonomous agents is crucial. Thank you for your insightful work @mmitchell.bsky.social @evijit.io @sashamtl.bsky.social @giadapistilli.com
Reposted
I guess the equivalent in AI agent(cy) engineering, the equivalent transition will be towards the method design and decomposition: dialogue? multi-role debate? argument tree? the data model the model is operating on top? Reward design for RL post-training/fine-tuning?
February 5, 2025 at 1:07 AM
I guess the equivalent in AI agent(cy) engineering, the equivalent transition will be towards the method design and decomposition: dialogue? multi-role debate? argument tree? the data model the model is operating on top? Reward design for RL post-training/fine-tuning?
Reposted
(take not mine) the current AI/agent(cy) engineering is much like pre-DL computer vision, when people tried to massage the problem around a few fairly rigid algos like SIFT. There also was RAG: scikit-image.org/docs/stable/... and also didn't work very well
Region Adjacency Graphs (RAGs) — skimage 0.25.1 documentation
scikit-image.org
February 5, 2025 at 12:59 AM
(take not mine) the current AI/agent(cy) engineering is much like pre-DL computer vision, when people tried to massage the problem around a few fairly rigid algos like SIFT. There also was RAG: scikit-image.org/docs/stable/... and also didn't work very well
Good design. "Native" tool calling makes LLM APIs much more complex than they should be. Using just a single "tool" - code execution - to rule them all is better.
supercharge your LLM apps with smolagents 🔥
however cool your LLM is, without being agentic it can only go so far
enter smolagents: a new agent library by @hf.co to make the LLM write code, do analysis and automate boring stuff! huggingface.co/blog/smolage...
however cool your LLM is, without being agentic it can only go so far
enter smolagents: a new agent library by @hf.co to make the LLM write code, do analysis and automate boring stuff! huggingface.co/blog/smolage...
January 1, 2025 at 5:20 AM
Good design. "Native" tool calling makes LLM APIs much more complex than they should be. Using just a single "tool" - code execution - to rule them all is better.
Reposted
New post! OpenAI's o1 using "search" was a PSYOP.
How to understand OpenAI's o1 models as really just one wacky, wonderful, long chain of thought.
A fun one trying to communicate intuitions for what large scale RL training does to LLMs. Much more to explore here in 2025!
How to understand OpenAI's o1 models as really just one wacky, wonderful, long chain of thought.
A fun one trying to communicate intuitions for what large scale RL training does to LLMs. Much more to explore here in 2025!
OpenAI's o1 using "search" was a PSYOP
How to understand OpenAI's o1 models as really just one wacky, wonderful, long chain of thought
buff.ly
December 4, 2024 at 3:33 PM
New post! OpenAI's o1 using "search" was a PSYOP.
How to understand OpenAI's o1 models as really just one wacky, wonderful, long chain of thought.
A fun one trying to communicate intuitions for what large scale RL training does to LLMs. Much more to explore here in 2025!
How to understand OpenAI's o1 models as really just one wacky, wonderful, long chain of thought.
A fun one trying to communicate intuitions for what large scale RL training does to LLMs. Much more to explore here in 2025!
Reposted
Novel disease, flu-like symptoms, high mortality especially in women and children.
On base rates, this is probably not going to be the next pandemic - but it should remind us that even in the wake of COVID-19, we have utterly failed to prepare to prevent such pandemics in the future.
On base rates, this is probably not going to be the next pandemic - but it should remind us that even in the wake of COVID-19, we have utterly failed to prepare to prevent such pandemics in the future.
Unknown disease kills 143 in southwest Congo, local authorities say
An unknown disease killed 143 people in Democratic Republic of the Congo's southwestern province in November, local authorities told Reuters.
www.reuters.com
December 3, 2024 at 6:14 PM
Novel disease, flu-like symptoms, high mortality especially in women and children.
On base rates, this is probably not going to be the next pandemic - but it should remind us that even in the wake of COVID-19, we have utterly failed to prepare to prevent such pandemics in the future.
On base rates, this is probably not going to be the next pandemic - but it should remind us that even in the wake of COVID-19, we have utterly failed to prepare to prevent such pandemics in the future.