Show HN: Onboard-CLI, a LLM powered and AST-based tool to visualize codebase
Article URL: https://github.com/animesh-94/Onboard-CLI Comments URL: https://news.ycombinator.com/item?id=48836813 Points: 3 # Comments: 0
Communities 6915 stories
4-bit GLM-5.2 (753B MoE) on 4× DGX Spark: 70.8% on Terminal-Bench 2.1 vs 81.0% for the full model
TL;DR: Full GLM-5.2 (753B MoE) quantized to Int4-Int8Mix + NVFP4 4-bit KV cache, TP=4 across 4× DGX Spark (GB10) at 100K context, run on Terminal-Bench 2.1…
FAANG Simulator
Article URL: https://www.abeyk.com/escape-the-rat-race/ Comments URL: https://news.ycombinator.com/item?id=48836778 Points: 11 # Comments: 2
Show HN: Hnwork.app – UI for Who is hiring posts
Hey HN, I built a UI on top of the "Who is hiring" posts. Take a look at https://hnwork.app!One of the downsides of unstructured text posts…
Slughorn, Slug font/glyph render lib for OpenGL/OSG/Vulkan/GPU APIs (MIT lic))
Article URL: https://alphapixeldev.com/slughorn-mit-licensed-gpu-agnostic-slug-font-glyph-rendering-library-for-opengl-osg-vulkan-and-all-gpu-driven-graphics-apis/ Comments URL: https://news.ycombinator.com/item?id=48836677 Points: 3 # Comments: 1
I was tired of agent frameworks burning tokens on polling loops, so I built a reactive node network that runs entirely on local models
Solo side project I've been hacking on for months, finally sharing it. (btw an example of what you can do on the demo video ^^, more…
Childhood and Education #20: Phones and Screens
We have a respite, so I thought I’d tackle various thoughts on children, phones and screens. GPT-5.6-Sol drops tomorrow, and the Fable agents are hard at…
Almost Always Unsigned
Article URL: https://graphitemaster.github.io/aau/ Comments URL: https://news.ycombinator.com/item?id=48836431 Points: 11 # Comments: 0
New Sweden: the US's long-lost 'secret' colony
Article URL: https://www.bbc.com/travel/article/20260629-new-sweden-the-uss-long-lost-secret-colony Comments URL: https://news.ycombinator.com/item?id=48836324 Points: 12 # Comments: 0
Cloudflare Drop
Article URL: https://www.cloudflare.com/drop/ Comments URL: https://news.ycombinator.com/item?id=48836233 Points: 61 # Comments: 34
Can the U.S. and China Deny AI?
Summary: Right now, we have no idea how practical it is for countries to sabotage each others’ AI projects. This makes it hard to forecast what…
A Real-Life Example of an Aligned System Killing Hundreds of People
I wrote this piece while at the AFFINE Superintelligence Alignment Seminar during discussions about the difference between AI Alignment and AI Safety. If you’re simply interested…
Complete local model asset generation pipeline
So I figured I'd update the community given I just shipped a nice little feature set and feel like sharing it finally :) In the past…
Distilled DeepSeek into Gemma 4 26B-A4B vs 12B. Not very useful, but I learned a lot.
So I decided to learn how to fine-tune LLMs. Read a few guides from Unsloth, poked around, then stumbled on Unsloth Studio and wanted to test…
Agentic safety triggers aren’t textual safety triggers — MCP attacks that beat SOTA guardrails more than half the time (code + dataset) [R]
Most safety alignment work treats "detect the attack" as a text classification problem — does the prompt contain language the model's safety guardrails should catch. That…
Notes on technical alignment via human-like social drives
1. Frontmatter1.1 Backstory for this postAs discussed in Intro to Brain-Like-AGI Safety, I’m working on the technical alignment problem for a hypothetical future “brain-like AGI”, with…
OpenMandriva: Statement regarding attempted distribution sabotage
Article URL: https://forum.openmandriva.org/t/statement-regarding-attempted-distribution-sabotage/8997 Comments URL: https://news.ycombinator.com/item?id=48835439 Points: 3 # Comments: 0
AI has completely revolutionized how I play RPGs
Crossposting this here because I thought you guys might appreciate it. When ChatGPT and other open source LLMs first came out, there was a lot of…
Grok 4.5
Article URL: https://x.ai/news/grok-4-5 Comments URL: https://news.ycombinator.com/item?id=48835111 Points: 32 # Comments: 14
LingBot-Video: sparse-MoE video diffusion transformer (13B total, 1.4B active) post-trained as an action-conditioned world model[R]
Single-stream diffusion transformer with a DeepSeek-V3-style sparse MoE (128 experts, top-8 routing, 1.4B active of 13B total). Six-reward RL post-training including a physical-plausibility reward, plus an…
I created a 140 GB IQ2_XXS REAP quant of GLM 5.2 for coding. Looking for testers.
GLM-5.2-504B-Code-GGUF is an imatrix calibrated quant of the most liked REAP, which is 0xSero/GLM-5.2-REAP-504B-GGUF. I also uploaded the imatrix file and the modified llama-quant.cpp so you…
Running GLM 5.2 on 4xGB10 with a 100G Switch, 330k ctx, ~25 t/s tg, ~650 t/s pp
TP4+DCP2 for a ~360k kV pool. Prefill increases to 900-1000 t/s with longer prompts. You can also run DCP4 for 660k, but prefill gets shaved to…
Subliminal Learning Happens at Every Rank, Given the Right Learning Rate and Enough Data
Subliminal learning is the phenomenon where a language model picks up a behavioral trait—such as fondness for cats—by training on data from a trait-carrying teacher that…
Show HN: Microsoft releases Flint, a visualization language for AI agents
Data visualizations are the bridge between user and data.But building AI agents that can generate visualizations reliably can be very tricky:- simple chart specs can be…