Skip to content
Standard
Reader
Log in
Tag
Llm
Articles and publications tagged Llm across the Atmosphere.
236
articles
109
publications
Articles
Publications
Recent
Recent
Trending
Most popular
Backroom
·
Oct 11, 2026
個人AI環境を30万円で構築する――画像生成、ローカルLLM、そして計算資源の所有
MIRAの写真生成をきっかけに、Mac miniの構成、Draw Things、ローカルLLMによるPython開発、そして計算資源の所有とクラウド利用について考えた対話記録。
local-ai
·
mac
Markus Kniebes
·
Oct 10, 2026
Warum AI‑Slop hinausposaunen
LLM
Markus Kniebes
·
Oct 9, 2026
LGTM (Looks Good to Me) - Claude Opus 5.5 music ...
LLM
Bailey's Retrospective
·
Oct 4, 2026
A pocket full of personal software
A year-ish spent building software I want, the way I want with *in a low voice* llms
9
·
5
·
software development
·
llm
grumpycat tech stories.
·
Oct 1, 2026
Process Sandboxing & Agents (in 5min)
Linux sandboxing for the win.
llm
·
localllama
-=Kernel-Error=-
·
Sep 26, 2026
Anthropic Cyber Verification Program: wie ich Claude für Security-Arbeit freigeschaltet habe und für wen sich das lohnt
Mitten in einer Claude-Code-Session hat Opus 5.5 meine Anfrage als Cyber-Risiko markiert und an ein schwächeres Modell abgegeben. Wer Pentests, Bug Bounty oder Responsible Disclosure macht, kann sich über das Cyber Verification Program von Anthropic freischalten lassen. Ich habe das heute gemacht: Ablauf, Ausweisprüfung, Bedingungen und Grenzen.
AI
·
Anthropic
Bryan Anthonio
·
Sep 26, 2026
Jev by Example
Exploring Jev, TypeSafe AI’s new AI model that returns probabilities instead of prose.
llm
·
machine-learning
lu.is
·
Sep 25, 2026
What a Harness Can Promise That a Prompt Can't
A short follow-up to "What Is a Harness?": two concrete checks a Wikipedia citation harness can make that a chat prompt cannot, and why they cost more work.
llm
·
wikipedia
Svenssons Nyheter
·
Sep 24, 2026
Bokmässan – allt mer problematisk
Jag besökte årets bokmässa på torsdagen precis som jag brukar göra. Jag kan konstatera att det numera ocks är väldigt mycket folk på torsdagar. Förr brukade det vara ganska tomt på förmiddagen men nu var de smockfullt redan från klockan 10. De stora förlagen, glasögonförsäljare och andra prylsförsäljare tar också upp en allt större plats.
Bokmässan
·
Bokmässan 2026
Random Thoughts
·
Sep 23, 2026
I (kind of) writing code by hand.
LLM
·
ai agents
gwlthr
·
Sep 22, 2026
With the release of GPT-6, GPT-6 Sol xhigh seems like a good tradeoff between price and performance when compared with Astra and Fable. Will for sure give it a try going forward.
llm
·
ai-agents
jola.dev
·
Sep 22, 2026
AI is antithetical to learning
LLM agents can write a lot of code for you very fast, but they also take away opportunities to learn and grow.
ai
·
llm
半ちゃーはん特盛りテック別館
·
Sep 13, 2026
ベクトル検索だけだと型番や固有名詞に弱い？ハイブリッド検索（BM25＋ベクトル）で回答精度を向上させる方法（シングルサイト編）
1. なぜ「ハイブリッド検索」が必要なのか？ WordPressの標準検索機能に対し、「表記揺れでヒットしない」「精度が悪い」といった不満を解決するため、OpenAI ＋ Qdrant ＋ Groq による超高速なAI検 […]
精度向上
·
LLM
Jeff Auriemma
·
Sep 10, 2026
A functional taxonomy for LLM inference in agentic tasks
A framework for understanding where LLM inference goes during agentic tasks: Initialization, Reasoning, Orchestration, and Synthesis. Consider "Reasoning Yield" as a way to measure how much inference is spent resolving uncertainty rather than mechanically advancing already-determined execution.
llm
·
mcp
Stefantastisch.de
·
Sep 9, 2026
Job-Advice
Wenn Ihr dauerhaft mehrere #KI-Agenten gleichzeitig betreuen müsst: RENNT!
Agent
·
AI
Notes of Olai Basile
·
Sep 6, 2026
Presidential Administrations, Scored by AI
Three frontier models, same question, same scale. The models approached the scoring differently, but agreed on the ordering: Trump-I is worse than Biden and Obama. Trump-II is worse than Trump-I.
LLM
·
PresidentialActions
Svenssons Nyheter
·
Sep 5, 2026
Att Sverige har billig el är lockande för AI-företagen
Allt fler datacenter växer upp i Sverige. Bara en del av dem är dock till för AI, De flesta är för helt vanliga data, servrar för onlinetjänster och molntjänster av diverse slag. Det är i huvudsak US-amerikanska storföretag som Facebook, Amazon, Google och Microsoft som bygger dem.
AI
·
Amazon
Redowan's Reflections
·
Sep 4, 2026
The irrational effectiveness of the Pi harness
A month of coding with Pi, its small agent loop, and the skills and extensions I've added to it.
LLM
·
CLI
Markus Kniebes
·
Sep 3, 2026
Privat programmiere ich ausnahmslos ohne ...
LLM
·
Claude Code
💌 Tiny Improvements - for builders, by @MikeBifulco.com
·
Sep 3, 2026
Why your prompt cache hit rate is zero: the silent invalidators
Prompt caching is a prefix match: one changing byte near the top of your prompt drops your hit rate to zero. A timestamp is the obvious culprit - here are the rest.
ai
·
llm
💌 Tiny Improvements - for builders, by @MikeBifulco.com
·
Sep 3, 2026
Your LLM doesn't know what day it is: date handling for AI tool calls
If you're building AI features into your product, your model has no idea what day it is - and it will confidently guess. Here's how to fix it.
ai
·
llm
permablog
·
Aug 31, 2026
Am I a Rust developer?
deep knowledge, and why everyone using agents is now a site reliability engineer
1
·
llm
·
rust
Mahib's Margins
·
Aug 28, 2026
DINO (Distillation with No Labels)
Breakdown of DINOv3 model that scales self-supervised learning (SSL) for images to produce our strongest universal vision backbones, enabling breakthrough performance across diverse domains.
ai
·
computer vision
Blog - Blog
·
Aug 24, 2026
LARGE Language Model
IA
·
IntelligenceArtificielle
Home
Latest
Discover
Search
