Fabrizio Milo Profile
Fabrizio Milo

@fabmilo

Followers
835
Following
4K
Media
438
Statuses
2K

LF angels investors (inception phase) AI for Software Development at Scale. I believe: - English is the new programming language - Code will eat the world

San Francisco
Joined November 2009
Don't wanna be here? Send us removal request.
@fabmilo
Fabrizio Milo
3 months
Created with @NotebookLM after discussing these topics with @Cyndesama @tensorqt @Niccolg92 and few others
1
0
11
@fabmilo
Fabrizio Milo
4 days
THE multi hop agentic benchmark is out. Talk is cheap, show me the run.
@alexgshaw
Alex Shaw
5 days
Today, we’re announcing the next chapter of Terminal-Bench with two releases: 1. Harbor, a new package for running sandboxed agent rollouts at scale 2. Terminal-Bench 2.0, a harder version of Terminal-Bench with increased verification
0
0
5
@fabmilo
Fabrizio Milo
5 days
Great work by @Mike_A_Merrill and @alexgshaw on Terminal Bench 2.0 with @LaudeInstitute here at @databricks
0
0
4
@fabmilo
Fabrizio Milo
6 days
The people crazy enough to think they can compress the world into a latent space are the ones who do
0
0
1
@fabmilo
Fabrizio Milo
8 days
Just opening and closing claude code costs me $0.0005 is just me because of some of my settings ?
0
0
2
@fabmilo
Fabrizio Milo
8 days
This thing is huge
@Teknium
Teknium (e/λ)
9 days
What dis
0
0
1
@fabmilo
Fabrizio Milo
8 days
The Real Arena for AI Agents
@icanvardar
Can Vardar
9 days
i got an idea
0
0
5
@fabmilo
Fabrizio Milo
9 days
Love this new feature of @googlechrome to split view two tabs
0
0
0
@fabmilo
Fabrizio Milo
11 days
I think Terminal Bench is the one true benchmark for multistep coding agent intelligence . Looking forward to attending the event.
@MLflow
MLflow
11 days
Only a few days left until the 𝗧𝗲𝗿𝗺𝗶𝗻𝗮𝗹 𝗕𝗲𝗻𝗰𝗵 𝗠𝗲𝗲𝘁𝘂𝗽 at @databricks HQ! 🚀 📣 Join the #MLflow community this Thursday for an evening of demos, discussions, and new announcements from Terminal Bench 2.0. Hear from Danny Chiao on building high-quality agents
1
0
0
@fabmilo
Fabrizio Milo
11 days
63 frames took 10 minutes to generate this Minecraft world model video from Open Oasis on my Apple M4, by just changing the Torch backend from CUDA to MPS. Can I make it go faster?
0
0
0
@fabmilo
Fabrizio Milo
12 days
Catching up on world models? this is a good read to review the history that lead to current state of the art AI and have a mental framework to categorize the various projects.
1
0
0
@fabmilo
Fabrizio Milo
12 days
Completed this nice intro RL course by @DeepLearningAI and @realSharonZhou it goes through the whole process of building a modern RL pipeline from training to production.
0
0
3
@fabmilo
Fabrizio Milo
13 days
This explains why the other coding models have been deprecated. Definitely another powerful move in the coding space. Cerebras is unbeatable in speed and speed in the coding operational loop is important. I am actually curious to try this one.
@cerebras
Cerebras
13 days
Today, @cognition released SWE-1.5 – the world’s fastest coding agent, powered by Cerebras. SWE-1.5 achieves frontier-level coding ability, comparable to Sonnet 4.5 and surpassing GPT-5. Cerebras and Cognition engineers worked hand in hand over the past few weeks, training a
0
0
0
@fabmilo
Fabrizio Milo
13 days
I think the main issue for independent vibe coders is cost, many have different accounts (openai / codex / openrouter) for various reasons and they want to utilize those credits before spending more money even if they have to do some extra manual work . If they are in big
@beyang
Beyang
13 days
Man, I think people using model-selector coding agents still don't appreciate the power of Amp's agent-oriented architecture. Here's a thread where main agent got it wrong, so I just asked it to use the oracle subagent and voila—bug fixed! https://t.co/lxsNB0ngww
1
0
0
@fabmilo
Fabrizio Milo
15 days
Zero installation is huge . It feels like internet explorer era all over again
@code
Visual Studio Code
15 days
OpenAI Codex is now integrated directly in @code through the new Agent Sessions view - and can be powered by your GitHub Copilot subscription. Try it out now with VS Code Insiders and a Copilot Pro+ subscription. Happy coding!
0
0
2
@fabmilo
Fabrizio Milo
15 days
Very strategic move from GitHub. They still own the entire workflow, how those files are changed is not their concern.
@techfrenAJ
techfren
15 days
@github bringing all coding agents in one platform under one subscription with their new "Agent HQ" What will this unlock? Agent to Agent collaboration? Orchestration? I will find out more on the vision today as I have been given the opportunity to interview some leads
0
0
1
@fabmilo
Fabrizio Milo
16 days
Interesting research from my university research lab on leveraging the property of “injectivity” of LLM prompts.
@GladiaLab
GLADIA Research Lab
16 days
LLMs are injective and invertible. In our new paper, we show that different prompts always map to different embeddings, and this property can be used to recover input tokens from individual embeddings in latent space. (1/6)
1
0
3
@fabmilo
Fabrizio Milo
16 days
MiniMax M2 is free until Nov 7th. Here is how you can configure claude code to use it.
@cedric_chee
cedric
16 days
@MiniMax__AI How to setup MiniMax-M2 in Claude Code, Codex CLI, Cline, etc. via compatible Anthropic API: https://t.co/TilKREMDww Took me some time to hunt this down. Thank me later.
0
0
0