RIP your old Claude prompts Opus 4.7 dropped 3 weeks ago and it follows instructions LITERALLY now. It scores 87.6% on SWE-bench (vs 80.8% on 4.6) but every prompt tuned for 4.6 is silently failing. 7 fixes that stopped my outputs from getting worse:
GENERATIVE AI
-
Agentic coding as machine learning
By
–
Agentic coding is a form of machine learning. Generated code is best treated as a blackbox artifact whose behavior and generalization should be managed via empirical evaluation, like with any ML model.
-
Gary Marcus on AGI and scaling limits
By
–
So many people misremember (or never read) what I said in in 2022 in “Deep learning is hitting a wall”, which was neither about revenue or AI’s potential upper limits. Rather, it was an argument that the pure of scaling LLMs would not get us to AGI, and that we would need to
-
Local LLM capabilities and AGI potential
By
–
Imagine seeing how capable Qwen 3.6 27B is when you give it web access and a proper harness and not yet getting that AGI will run locally Ngmi
-
Early Look at Imagine Agent Mode for Image and Video Generation on Grok App
By
–
Early look at Imagine Agent Mode on Grok app for iOS!
— 🚨 AI News | TestingCatalog (@testingcatalog) 9 mai 2026
Users will be able to use Imagine Agent via a mobile optimised native UI to generate images and videos that require more complex workflows.
SpaceXAI is getting quite ahead of everyone else on this front!
We just need… pic.twitter.com/5QxeCclHEoEarly look at Imagine Agent Mode on Grok app for iOS! Users will be able to use Imagine Agent via a mobile optimised native UI to generate images and videos that require more complex workflows. SpaceXAI is getting quite ahead of everyone else on this front! We just need
-
How Human Prompting Influences AI Model Benchmarks
By
–
mythos obviously looks incredibly capable and im psyched to use it also if you're panicking about it: benchmarks don't measure model capability alone they measure model capability after a human has done the work of finding a prompt that lets the model’s capability appear that
-
The rising value of human-AI creative collaboration
By
–
as ai makes imitation cheaper and cheaper the value of using AI and your brain to make totally new things goes up
-
MiniCPM-o 4.5 for omni-modal interactions
By
–
MiniCPM-o 4.5 Towards Real-Time Full-Duplex Omni-Modal Interaction paper: https://
huggingface.co/papers/2604.27
393
… -
Tutorial on building production-grade AI agents
By
–
Voici la vidéo pour apprendre comment construire des agents d'IA de production.
— Jouhatsu | AI Influence Operator (@Jouhatsu_ai) 9 mai 2026
30 minutes. gratuit. par les ingénieurs qui l'ont construit. pic.twitter.com/u3z3EvKMySVoici la vidéo pour apprendre comment construire des agents d'IA de production. 30 minutes. gratuit. par les ingénieurs qui l'ont construit.
-
Iterative improvement loops for AI agent development
By
–
the best teams building agents ship early and iterate quickly you can't just ship an agent and then forget about the key to getting the best agents is to build an iterative improvement loop