"everything is a file" becomes "everything is context." CSIRO Data61 and ArcBlock published a paper applying the oldest Unix principle to the newest AI problem. they propose treating memory, tools, knowledge, and human input as a mounted filesystem that agents browse at runtime
SOFTWARE
-
LM Studio Model Performance: GPT OSS 120B Impresses
By
–
I’ll believe it when I see it. So far I have not been impressed with any other model in LM studio aside from GPT OSS 120B.
-
joyfl v0.7: Stack Manipulation Puzzle Solver Framework
By
–
joyfl — v0.7: Quotation Solver Newest release last week uses the existing search framework to find matching program fragments. It's like using a sudoku solver to discover solutions for stack manipulation puzzles, based on user-provided tests.
-
Scobleizer compares three dictation apps: Mostly Typeless, Wispr, Monologue.
By
–
Mostly Typeless since that's what I started with. Wispr is more popular. Monologue is newer and I'm trying to see if it really is any better than the other two.
-
Wispr Flow, Typeless, Monologue: stunningly good speech-to-text
By
–
Wispr Flow or Typeless or Monologue. They are way better than anything else. It's hard to tell the difference between these three. They are stunningly good.
-
TorchLean: First Fully Verified Neural Network Framework in Lean
By
–
Super excited to release TorchLean!! I’m happy to answer questions and would love to discuss verified NNs + theorem proving especially what it’ll take for the field to become widely usable in real ML systems. Blog post + codebase release soon! Prof. Anima Anandkumar (@AnimaAnandkumar) We’re excited to release TorchLean which is the first fully verified neural network framework in Lean. The Lean community has largely focused on pure mathematics. TorchLean expands this frontier toward verified neural network software and scientific computing. With the recent release of CSlib, we see this as another step toward a fully verified ML stack. We support features: 1. Executable IEEE-754 floating-point semantics (and extensible alternative FP models) verified tensor abstractions with precise shape/indexing semantics 2. Formally verified autograd system for differentiation of NN programs Proof-checked certification / verification algorithms like CROWN (robustness, bounds, etc.) 3. PyTorch-inspired modeling API with eager-style development + export/lowering to a shared IR for execution and verification Project page: leandojo.org/torchlean.html Paper: [2602.22631] TorchLean: Formalizing Neural Networks in Lean Work done @Robertljg, Jennifer Cruden, Xiangru Zhong, @huan_zhang12 and @AnimaAnandkumar. #MachineLearning #ScientificComputing #Lean — https://nitter.net/AnimaAnandkumar/status/2027907453908857298#m
→ View original post on X — @animaanandkumar, 2026-03-01 22:38 UTC
-
Anthropic Launches Memory Import from ChatGPT and Gemini
By
–
Anthropic absolutely nailed this. So many people will start using Claude. New feature lets you import your *entire* memory from ChatGPT, Gemini etc into Claude so it *instantly* knows everything about you. No more reminding Claude who you are. The best fucking part is it takes literally 60 seconds: – Copy and paste the below prompt into your alternative AI (e.g. ChatGPT) – Paste answer into Claude's "memory" settings and… you're done. – Claude immediately picks up from the last conversation you had with it in ChatGPT! The opportunity cost to switch to Anthropic just went to zero – their app is currently #1 in the app store — Greg (@GregFeingold) Ready to make the switch? claude.com/import-memory [Translated from EN to English]
→ View original post on X — @flashtweet, 2026-03-01 03:34 UTC
-
TorchLean: First Fully Verified Neural Network Framework in Lean
By
–
We’re excited to release TorchLean which is the first fully verified neural network framework in Lean. The Lean community has largely focused on pure mathematics. TorchLean expands this frontier toward verified neural network software and scientific computing. With the recent release of CSlib, we see this as another step toward a fully verified ML stack. We support features: 1. Executable IEEE-754 floating-point semantics (and extensible alternative FP models) verified tensor abstractions with precise shape/indexing semantics 2. Formally verified autograd system for differentiation of NN programs Proof-checked certification / verification algorithms like CROWN (robustness, bounds, etc.) 3. PyTorch-inspired modeling API with eager-style development + export/lowering to a shared IR for execution and verification Project page: leandojo.org/torchlean.html Paper: [2602.22631] TorchLean: Formalizing Neural Networks in Lean Work done @Robertljg, Jennifer Cruden, Xiangru Zhong, @huan_zhang12 and @AnimaAnandkumar. #MachineLearning #ScientificComputing #Lean
→ View original post on X — @animaanandkumar, 2026-03-01 00:43 UTC
-
XGBoost: A Reliable Machine Learning Algorithm
By
–
Just remember: no matter how bad things get out there, you can always count on XGBoost. @trainxgb