15469 articles tagged with LLM
RE: https://matriochka.intxiv.ru.com/@horzagger/117561030330930732L'#IA #AI #LLM ne sait pas lire ou plutôt elle sait lire ce que je n'ai jamais écrit ni affirmé ni cru ni pensé. M...
Embedding Models Matter More Than You ThinkYour LLM gets the glory. Your embedding model does the work. If you're not picking it with the same care as your foundation model, you're...
In-context learning: In-context learning is a language model's ability to pick up a task from examples or instructions in its prompt, with no retraining. How it works and fails. ht...
東京、一筋縄ではいきませんよブラックホール合体重力波「リングダウン」40年越しの謎、東大ら解明 https://news.mynavi.jp/techplus/article/20261105-5260787/#Apple #LLM #news #bot
#agentic / #LLM pro-tip:DO NOT USE PAPERCLIPHoly shit. It's got a massive problem with context management and will absolutely blow through tokens / subscription usage at an unbelie...
I think the most fascinating thing I discovered is that writing with LLM works better if you create a writing agent but separate out the agents/skill that critics, proofread and fa...
From now on if anyone shows you "art" that is obviously generated by an LLM, get in the habit of saying "wow that looks like shit, did you get an #AI to do it?"
🍀 #DiffuSpace Clover-35B-A3B-Preview is an open Mixture-of-Experts diffusion language model with 35B total and 3B active parameters plus a thinking mode, released under an Apache l...
Ik heb mijn AI-beleid nog wat herzien en uitgebreid: https://bartavi.nl/bericht/2026/ai-beleid/#ai #genai #llm
@BleepingComputer"The concern is that researchers may trust results the model silently changed"Nothing new here#llm
#LLM|s are the perfect social engineer. Here two versions where in one it tells me why Link from the legend of Zelda is a VC capitalist and in the other one why he is actually a ra...
Slashing AI Agent LLM Bills by 75%: Sub-Millisecond Context Compression and Semantic Prompt...
Reflections on Rust in the LLM Age — Bryan Cantrill | Rust NYC https://lobste.rs/s/yomksa #video #ai #rusthttps://www.youtube.com/watch?v=5D7QPOIZ7gY
Run untrusted LLM-generated code in a hardware-isolated sandbox with the network locked to an...
ヒトにはヒトの、亜人には亜人のPLaMoがあるのでしょうPLaMo 3 Translate：世界最高クラスの翻訳特化LLMの重み公開と開発秘話｜株式会社Preferred Networks https://www.preferred.jp/ja/blog/tech/plamo-3-translate-weight-release#Apple #LLM #ne...
RE: https://anarres.family/@faithisleaping/117564905548570621- and again, this is true for all LLM output. Just today I had to sit through a chatbot-themed session (don't fucking a...
Aion 2, an AI-driven prompt engineering resource, offers a pre-configured environment for advanced language model operations, ensuring...
#ai #llm #ram #stolenmemes
🔴 Making Immersive LLM Chat Experiences More Accessibleby @eric at @smashingmag #accessibility #AI #webdesign https://www.smashingmagazine.com/2026/11/making-immersive-llm-chat-exp...
"Computers are incredibly fast, accurate, and stupid. Human beings are incredibly slow, inaccurate,...
What #reverseengineering with #Ghidra combined with lokal #LLM model im #lmstudio sounds like:
The architecture of open-weight LLMs: MoE, hybrid layers, ternary weightshttps://www.silasdata.com/llm-playground-inside-architectures/#llm #llms
Serving Moonshot AI's Kimi K3.1 Pro with llm-d across TPUs and GPUs #llmd #ai https://twp.ai/9Ocwul
The Lisp curse, now coming to your ecosystemhttps://javahippie.net/programming/llm/2026/03/05/the-lisp-curse-coming-to-your-ecosystem.html#lisp #llm #programming