to be clear, im not even running inference. just like, 5 Codex threads + 1 Claude Code thread plus a few other things
LLMS
-
Running local AI agents reveals hardware compute bottlenecks
By
–
running agents on my laptop is the first time in a long time where i feel my computer is underpowered i could actually consume way more RAM and GPU if it was available
-
Claude Code sees 15x growth and SQL debugging feature
By
–
Guessing you're looking at npm-only data. We switched to a native installer a few months back, so the majority of installs aren't captured here. Thursday was the second-highest Claude Code signup day we've ever had (15x growth since Jan 1). Ask Claude to debug your SQL?
-
Managing AI Agents as Iterative Systems and Team Dynamics
By
–
viv always says it better than me lots of talk recently of thinking of agents as systems to measure and iteratively improve but – thats not JUST a technical thing. its also a human & team thing
-
The Shift from RAG to Knowledge Compilation in AI Memory
By
–
RAG is already becoming the “old way” The future of AI memory is not retrieval.
It’s compilation. Here’s the shift in one sentence: From searching information To structuring knowledge The new model? LLM Wiki Instead of: Chunking documents Running similarity -
Iterative Lifecycle for AI System Deployment
By
–
Evaluate before deploying Monitor after deploying Use what you learn to make the next version better
-
Official Claude Prompt Engineering Course
By
–
Apprendre comment bien prompter Claude. 24 minutes. gratuit. par les gens qui l'ont construit.
-
Anthropic engineer shares 100% AI-generated coding workflow
By
–
Le responsable de Claude Code chez Anthropic a déclaré qu'il n'avait pas écrit de code à la main depuis des mois.
— Jouhatsu | AI Influence Operator (@Jouhatsu_ai) 9 mai 2026
En 2 jours, il a livré 49 fonctionnalités complètes. Toutes écrites à 100 % par l'IA.
Il vient de publier une conférence de 30 minutes sur exactement comment il s'y… pic.twitter.com/psBjqY2nGwLe responsable de Claude Code chez Anthropic a déclaré qu'il n'avait pas écrit de code à la main depuis des mois. En 2 jours, il a livré 49 fonctionnalités complètes. Toutes écrites à 100 % par l'IA. Il vient de publier une conférence de 30 minutes sur exactement comment il s'y
-
Defining AI Agents as Systems Beyond the Model
By
–
agents are definitionally a system around a model lots more than a model!
-
DeepSeek v4 Flash Impresses Locally
By
–
OPEN SOURCE AI is killing it. DeepSeek v4 Flash is a quasi-frontier model with a massive 1M context window. It can LOCALLY on a 128GB Mac using specialized 2-bit quantization. Asked my OpenClaw Engineering Agent Ross about the model and he's impressed.