Roger Oriol retweeted
El gran examen de Softcatalà per trobar la millor IA en català
✍️ @BernatCastanyer naciodigital.cat/societat/el…
Roger Oriol retweeted
llama.cpp v1.0.0 is now available
huggingface.co/blog/ggml-org…
Build a Basic AI Agent From Scratch: Session Management II
ruxu.dev/articles/ai/build-a…
20
Build a Basic AI Agent From Scratch: Session Management
ruxu.dev/articles/ai/build-a…
21
Build a Basic AI Agent From Scratch: Memory
ruxu.dev/articles/ai/build-a…
2
94
Build a Basic AI Agent From Scratch: Security III
ruxu.dev/articles/ai/build-a…
Build a Basic AI Agent From Scratch: Security II
ruxu.dev/articles/ai/build-a…
1
55
Build A Basic AI Agent From Scratch: Human in the Loop & Security
ruxu.dev/articles/ai/build-a…
19
Build A Basic AI Agent From Scratch: Long Task Planning
ruxu.dev/articles/ai/build-a…
2
133
Next part from the basic AI agent series:
Build A Basic AI Agent From Scratch: Tools ruxu.dev/articles/ai/build-a…
Roger Oriol retweeted
I packaged up the "autoresearch" project into a new self-contained minimal repo if people would like to play over the weekend. It's basically nanochat LLM training core stripped down to a single-GPU, one file version of ~630 lines of code, then:
- the human iterates on the prompt (.md)
- the AI agent iterates on the training code (.py)
The goal is to engineer your agents to make the fastest research progress indefinitely and without any of your own involvement. In the image, every dot is a complete LLM training run that lasts exactly 5 minutes. The agent works in an autonomous loop on a git feature branch and accumulates git commits to the training script as it finds better settings (of lower validation loss by the end) of the neural network architecture, the optimizer, all the hyperparameters, etc. You can imagine comparing the research progress of different prompts, different agents, etc.
github.com/karpathy/autorese…
Part code, part sci-fi, and a pinch of psychosis :)
github.com/openai/codex Along with the launch of o3 and o4-mini, OpenAI has released a coding assitant for the terminal: Codex. You can use it to create new projects, make changes to existing projects or ask the model to explain code to you, all in the terminal.
1
121
It can use multimodal input, allows sandboxing your development environment to secure your computer and also allows the use of context files, ~/.codex/instructions.md for global instructions for Codex and ./codex.md in the project root for project-specific context.
1
52
After the unimpressive release of GPT-4.5 a month and a half ago, OpenAI is now releasing a new version - backwards. Today, they released three new models, exclusive to the API: GPT-4.1, GPT-4.1 mini and GPT-4.1 nano. openai.com/index/gpt-4-1/
1
61
We now have acknowledgement from LMArena of what we already knew: AI labs are cheating to get their models as high as possible in the LMArena leaderboard / benchmarks.
We've seen questions from the community about the latest release of Llama-4 on Arena. To ensure full transparency, we're releasing 2,000+ head-to-head battle results for public review. This includes user prompts, model responses, and user preferences. (link in next tweet)
Early analysis shows style and model response tone was an important factor (demonstrated in style control ranking), and we are conducting a deeper analysis to understand more! (Emoji control? 🤔)
In addition, we're also adding the HF version of Llama-4-Maverick to Arena, with leaderboard results published shortly. Meta’s interpretation of our policy did not match what we expect from model providers. Meta should have made it clearer that “Llama-4-Maverick-03-26-Experimental” was a customized model to optimize for human preference. As a result of that we are updating our leaderboard policies to reinforce our commitment to fair, reproducible evaluations so this confusion doesn’t occur in the future.
1
78





