Itay Katav

PhD candidate in Computer Science

[Fernando @Franc0Fernand0]

A few algorithms I regularly force myself to review so I don’t forget how they work:

• Kadane’s → Maximum subarray sum
• Rabin-Karp → Substring search with hashing
• Topological Sort → Ordering a DAG
• Prim’s → Minimum Spanning Tree
• Kruskal’s → MST with Union-Find
• Dijkstra’s → Shortest path (no negative weights)
• Bellman-Ford → Shortest path (with negative weights)
• Tarjan’s → Strongly Connected Components
• Backtracking → Sudoku Solver

These are the ones I keep coming back to years later.

Which algorithms do you still periodically revisit?

[Yong Zheng-Xin @yong_zhengxin]

Joining @openai next month!

after seeing people's reaction to Alisa's post about her experience, I also wrote down some of the surprising things I wish I know before my research scientist job search: https://t.co/vyFV6lYpWD

[Sebastian Raschka @rasbt]

https://t.co/L4s34f28oX

[Binfeng Xu @billxbf]

Excited to release 🌟Polar🌟, our Agent RL rollout infra for real-world harnesses. Be it Codex, Claude Code, OpenClaw, Hermes, or your self-made ones 🔥 -- Polar takes your harnesses directly as training environments without code change.

Find a problem, design the harness, and train your own agents! 🧵

[Ryan Bahlous-Boldi @RyanBoldi]

Your RL post-training may be sabotaging your LLM’s test-time scaling!

Conventional RL pretends that you can collapse all reward signals *upfront* into a single *scalar reward*.
We introduce Vector Policy Optimization (VPO), which natively maximizes *vector-valued* rewards, boosting test time search performance, even on the original scalar.

[Sapient Intelligence @Sapient_Int]

Introducing HRM-Text.

An ultra-lean 1B-parameter reasoning language model designed to deliver strong general performance with a fraction of the data, compute, and infrastructure.

Trained on just 40B structured tokens, HRM-Text achieves competitive performance while using ~1/1000 of the training data of comparable models.

The kicker? The full model trains in roughly one day on a $1,000 budget.

This opens the door to a new generation of AI that is powerful, accessible, and radically easier to adapt. Theories and research concepts once deemed too expensive to test are officially back in the game.

Sapient Intelligence invites you to help us shape a new paradigm for general intelligence.

[Thariq @trq212]

I put a lot of heart into my technical writing, I hope it's useful to you all.

📌 Here's a pinned thread of everything I've written.

(much of this will be posted on the Claude blog soon as well)

[PyTorch @PyTorch]

Need to cut LLM training checkpoint costs?

Training LLMs requires periodic checkpoints, full snapshots of model weights, optimizer states, and gradients saved to storage so training can resume after interruptions. At scale, these checkpoints become massive. NVIDIA nvCOMP is a GPU-accelerated lossless compression library that compresses the checkpoint before it leaves GPU memory, no roundtrip – no extra data movement.

Developers can easily integrate high-throughput compression directly into their Python workflows (such as PyTorch or TensorFlow).

🔗 Read the full post:
https://t.co/EcPB5MPL9c

#PyTorch #OpenSourceAI #AI #Inference #Innovation

[Eric S. Raymond @esrtweet]

I'm a software engineer with 50 years of experience. If you know how to steer an LLM properly, the frontier models are extremely good at generating code. They're weak at architecture, which is one of several reasons you want a human in the loop, but they can have a very low error rate compared to most humans.

When they don't - when they generate slop - it's because you didn't know how to use the tool correctly.

[finbarr @finbarrtimbers]

For Olmo 3, we moved from a synchronous RL setup to an asynchronous one. This made our code 4x faster in terms of throughput (tokens/second).

I wrote about the changes in the paper, but I finally found the time to go deeper on what was involved:

https://t.co/7aky9ouxYU

[Itay Katav @ItayKatav]

@Gorgc

[Itay Katav @ItayKatav]

@Punk9203 amazing dude

[Itay Katav @ItayKatav]

@JHFonseca @alifarhat79 @aIifarhat79_

[Itay Katav @ItayKatav]

@elonmusk @BillyM2k @alifarhat79

[Itay Katav @ItayKatav]

@Gorgc red

[Itay Katav @ItayKatav]

@HeroDividend @alifarhat79 good one

[Itay Katav @ItayKatav]

@alifarhat79 hold the line bi*ches

[Itay Katav @ItayKatav]

@codeurDE @ROSHTEINS thanks dude

[Itay Katav @ItayKatav]

@codeurDE @ROSHTEINS yo man I have the same pc but I can connect only 1 monitor
how did you end connecting 3?