New8 min read
Anthropic Discovers J-Space: A Global Workspace Inside Language Models
Anthropic's new research reveals LLMs have an internal 'workspace' for silent reasoning - and it could change how we build safer AI.
LLMS
23 articles
LATEST
AI Tutor Shows 0.71-1.30 SD Effect Size in Dartmouth Statistics Course
A new study from Dartmouth measures the impact of an AI tutoring platform on introductory statistics performance. Full engagement with the system correlated with significant exam score improvements, though selection bias remains a key limitation.
•8 min read
Read Article
New6 min read
Why Price Per 1M Tokens Is a Misleading Metric for LLM Costs
Comparing LLMs by token pricing alone can lead you to choose worse, more expensive models. Cost per task tells the real story.
Read more
7 min read
Vulnerability Reports Are Not Special Anymore
Filippo Valsorda argues that LLMs have ended the era of treating security researchers with kid gloves. When anyone can discover vulnerabilities with an AI, the old coordinated disclosure model breaks down.
Read more
7 min read
GLM-5.2 Local Deployment: Running Z.ai's 744B Model on Consumer Hardware
Unsloth's dynamic quantization makes GLM-5.2 runnable on a 256GB Mac or a 24GB GPU with CPU offloading. Here is the hardware math, the quantization tradeoffs, and what the HN community learned from actually running it.
6 min read
VibeThinker-3B: A 3 Billion Parameter Model That Outscores Opus 4.5 on Reasoning
A new paper shows a 3B parameter model hitting 94.3 on AIME26 and 96.1% on LeetCode contests - matching or exceeding models 100x its size. The catch: it traded general knowledge for pure reasoning ability.
6 min read
Apertus: Europe's Answer to AI Sovereignty - and Why HN Is Skeptical
Switzerland's fully open foundation model promises transparent training data and EU compliance. The HN crowd has questions about actual performance.
7 min read
Prompt Injection is Role Confusion - New ICML Research Explains Why LLMs Can't Tell Friend from Foe
New research from MIT reveals that LLMs identify speakers by writing style, not by tags - meaning attackers who sound like the system effectively become the system. The findings explain why prompt injection remains unsolved.
6 min read
GPT-5.5 Has a 3x Higher Hallucination Rate Than MIT-Licensed GLM-5.2
New benchmark data shows GPT-5.5 hallucinates 86% of the time when it does not know the answer - versus 28% for the open-weights GLM-5.2. The numbers challenge the assumption that bigger models equal more reliable output.
6 min read
LLM Architectures Got Complicated Fast
Modern LLMs now use MoE routing, mixed attention variants, and fused vision encoders. The simple transformer stack is gone - here's what replaced it and why it matters for developers.
8 min read
The Claude Tokenizer Change: What ~30% More Tokens Means for Your Bill
Anthropic's docs say the tokenizer introduced with Opus 4.7 can use up to 35% more tokens for the same text. Here is what that does to per-request cost, max_tokens, and cross-model comparisons.
10 min read
Fable 5 with 1M Context: What Actually Works in Practice
Fable 5 1M context workflows that actually work: whole-repo reviews, log archaeology, multi-doc synthesis - plus the honest math on when RAG still wins.
10 min read
Fable 5 Effort Levels Explained: low to xhigh, and What They Cost You
Fable 5 effort levels explained: what low, medium, high, xhigh, and max actually change, which models support each level, and how effort drives your token bill.
Read more
Showing 12 of 22 articles
Keep exploring LLMs
- - LLMs Topic Hub - tools and guides for LLMs from the Developers Digest directory
- - Glossary - dive deeper across the Developers Digest knowledge base
- - Developers Digest on YouTube - video tutorials covering LLMs and more
Get Smarter About AI Dev
New tutorials, open-source projects, and deep dives on coding agents - delivered weekly.
One email per weekReal code, not theoryFree forever
Explore 688 topics
Browse All Topics