DROP EVERYTHING The bible for running LLMs locally is now available online to read for free Covers what to use on – Laptop / edge / odd hardware
– Mac-first workflows
– Single RTX GPUs
– 2-4+ NVIDIA / CUDA GPUs
– General production serving
– Long-context / MoE / routing
–
SOFTWARE
-
The bible for running LLMs locally now free online
By
–
-
Mythos hacked NSA systems, export controls imposed on Mythos and Fable
By
–
Mythos broke into almost all of the NSA’s classified systems in hours, per its director. It would have been irresponsible to not impose export controls on it. (And on Fable, with its pathetically inadequate guardrails.)
-
Traditional manufacturing software vs AI-generated: bespoke in a week
By
–
Traditional manufacturing software: buy standard package, customize for months, vendor teams build features. AI-generated software: bespoke from day one, one week to production, any operator builds through prompts. Partner content with Cybus. #cybus_iiot pic.twitter.com/zkVkJWYcAZ
— Lucian Fogoros (@fogoros) 20 juin 2026Traditional manufacturing software: buy standard package, customize for months, vendor teams build features. AI-generated software: bespoke from day one, one week to production, any operator builds through prompts. Partner content with Cybus. #cybus_iiot
-
ColBERT outperforms on CPU with low latency for embeddings
By
–
I'm talking about individual descriptions used for embeddings. It doesn't need to be particularly long for late interaction to perform better. The tradeoff really depends on the use case. In this case, even on a cheap CPU, the latency is so low that ColBERT just works better!
-
PixelRAG skips OCR by embedding screenshots directly into vectors
By
–
True if you round-trip through OCR to markdown, that's where the token cost piles up. But PixelRAG skips that. The screenshot gets embedded straight into a vector for retrieval, no image to text step in the pipeline. The VLM only reads pixels at the end, on the few tiles it
-
Two-month pinned threads and recall of important elements
By
–
Yeah! I had pinned threads that continued for more than two months and codex still remembers all the important elements. Otherwise, it searches for important elements by scanning the session itself.
-
Don’t just add AI button, rebuild projects AI-first, e.g. hotelist
By
–
I normally don't like plugging on an AI chat into my projects, because it's seems too easy and basic
— @levelsio (@levelsio) 20 juin 2026
I think you should instead rebuild entire projects from the ground up to be AI first, not just add some AI button
But in this case https://t.co/kH0hX7mhQy is already AI from the… https://t.co/zRZ8IAHlxZ pic.twitter.com/4wVzmAGL6gI normally don't like plugging on an AI chat into my projects, because it's seems too easy and basic I think you should instead rebuild entire projects from the ground up to be AI first, not just add some AI button But in this case http://
hotelist.com is already AI from the -
Andrej Karpathy’s 2018 talk on Building the Software 2.0 Stack
By
–
The talk is "Building the Software 2 0 Stack (Andrej Karpathy)" 2018
-
PixelRAG: skip HTML parsing, screenshot for RAG
By
–
STOP PARSING HTML FOR RAG. JUST SCREENSHOT IT Researchers from UC Berkeley just released PixelRAG, an open-source system that skips HTML parsing entirely. Why is it changing web scraping for good? Well, instead of scraping a page into text and embedding chunks: #1 it
-
Cancelable Ear Recognition via Optimized Deep Feature Fusion
By
–
A Cancelable Ear Recognition System via Optimized Deep Feature Fusion! #BigData #Analytics #AI #MachineLearning #DataScience #IoT #IIoT #Python #RStats #TensorFlow #JavaScript #ReactJS #CloudComputing #Serverless #DataScientist #Linux #Programming #Coding #100DaysofCode