Paper: https://
arxiv.org/pdf/2603.20432
LLMS
-

Coding agents outperform long-context models
By
–
BREAKING: Duke researchers just proved that coding agents are better at processing long documents than models with million-token context windows. > Not because of longer context. Because grep and sed are better retrieval tools than attention. > +17.3% average improvement
-

Huawei’s Smart Noise Scheduler Improves Diffusion LLM Logic Learning
By
–
What if Diffusion LLMs learned logic more efficiently? Huawei's Noah's Ark Lab proposes a breakthrough: their "smart noise scheduler" uses priority masking to focus training on only information-dense data, making DLLMs master core reasoning and structure. This boosts average accuracy by 4% on Code & Math reasoning, beating uniform baselines and unlocking DLLM potential. Mask Is What DLLM Needs: A Masked Data Training Paradigm for Diffusion LLMs Paper: arxiv.org/abs/2603.15803 Dataset: huggingface.co/datasets/malr… Our report: mp.weixin.qq.com/s/1yTd36hev… 📬 #PapersAccepted by Jiqizhixin
→ View original post on X — @jiqizhixin, 2026-04-05 14:05 UTC
-
Learning Path: LLM Architecture, Reasoning Models, and Production Systems
By
–
I would probably start with 1. my Build A Large Language Model (From Scratch) book to understand the basic architecture and basic pipeline. Then maybe 2. Build A Reasoning Model (From Scratch) for inference scaling and reinforcement learning
3. Maybe one of the "production" -
Progressive Disclosure Pattern Optimizes AI Token Efficiency
By
–
We've been building skills at Towards AI for months now and the progressive disclosure pattern is key. Loading full context upfront wastes tokens and confuses the model. The lightweight trigger + on-demand loading is how you actually scale this. Super cool to see Anthropic
-
Python Rewrite and Architecture Leak Analysis Revealed
By
–
The Python rewrite angle is clever haha. Honestly the leak was more interesting for what it revealed about the architecture than anything else. Skills, hooks, the whole execution model… not that surprising if you use it daily but nice to see confirmed.
-
Intermediate Reasoning Steps in AI Models and Error Tolerance
By
–
This is a good reframe. The intermediate reasoning steps being "wrong" doesn't matter if the final output is correct. It's similar to how humans think through problems, lots of wrong turns before the right answer. The error compounding argument assumes each token is a final
-
LLMs democratizing government transparency through data processing
By
–
Government transparency limited by people's ability to process raw data is such an underrated problem. LLMs processing spending bills, lobbying disclosures, zoning decisions… this could genuinely change how democracy works at the local level. Super exciting.
-
2M Token Context: KV Cache Engineering Challenges and Limitations
By
–
2M token context sounds incredible but I wonder how it works in practice. KV cache at that scale is a real engineering problem, and results are quite often disappointing for higher context, especially for inter-connected questions that basically needs some sort of "retrieval"
-
GPT-5.5 Spud: OpenAI’s Next Major Model Breakthrough
By
–
Why i'm really excited for GPT-5.5 "Spud" As you know: OpenAI just finished pretraining its next major model, codenamed Spud. Altman told staff they expect a "very strong model" in weeks that can "really accelerate the economy." To free up compute, they're killing Sora entirely,