Models & Labs
Anthropic Removes 80% of Claude Code Prompts
Lev Selectorhigh confidence
Why it matters
- →Simplifies AI model interactions
- →Enhances model efficiency and performance
- →Reflects a shift towards minimalistic AI design
Anthropic has made a strategic decision to remove 80% of the internal prompts from its Claude Code. This change is based on the observation that excessive scaffolding can confuse advanced AI models. By simplifying the input, Anthropic aims to enhance the model's ability to process and understand tasks autonomously, leading to more efficient performance.
Read originalThe story around this
Earlier coverage that leads up to this article, and what followed. Lines connect each piece to the closest one after it, converging here.
How we got here
- 1Anthropic launches Claude Design for prototyping
The Rundown AI · April 20, 2026 · Related
- 2Anthropic Releases Official Claude Code Learning Resources
Duncan Rogoff · April 20, 2026 · Related
- 3Anthropic's Claude Code Revolutionizes Software Development
MIT Technology Review AI · May 21, 2026 · Same story
- 4Anthropic Increases Claude Code Usage Limits
Matt Wolfe · May 22, 2026 · Related
- 5Anthropic's Claude Opus 4.8 Model Focuses on Honesty
The Verge AI · May 28, 2026 · Related
- 6Anthropic releases Claude Opus 4.8
AI News · May 29, 2026 · Related
- 7Anthropic Reverses Controversial Claude Fable 5 Policy
WIRED AI · June 11, 2026 · Related
- 8Anthropic Launches In-App Browser for Claude Code
Matt Wolfe · July 29, 2026 · Related
What happened next
- 9Anthropic releases Claude Fable 5.1 with cheaper caching
Wes Roth · September 1, 2026 · Related
- 10Anthropic launches Claude Fable 5.1 model
The Rundown AI · September 2, 2026 · Related
- 11Claude Code v2.1.267 fixes prompt cache and session resume
Claude Code Releases · September 16, 2026 · Same story
- 12Anthropic releases official Claude Code playbook for Opus 5.5
Duncan Rogoff · September 23, 2026 · Same story
- 13Claude Code v2.1.316: Subagents and Gateway Budgets
Claude Code Releases · November 1, 2026 · Same story
Follow this story
Open the full story →Anthropic Engineers Optimize Claude Code Prompting
4 developments
- Jul 28 · Duncan Rogoff
Anthropic Engineers Optimize Claude Code Prompting - Jul 31 · Lev Selector
Anthropic Removes 80% of Claude Code Prompts (This article)↳ Anthropic removed 80% of internal prompts from Claude Code to improve model performance. - Aug 9 · TechCrunch AI
Anthropic Enables Auto Mode by Default in Claude Code↳ Anthropic sets auto mode as default for Claude Code Pro, Max, and Team accounts starting August 14 to streamline coding. - Aug 10 · The AI Daily Brief
Anthropic Defaults to Auto Mode for Claude Code
More in Models & Labs
Models & Labsother
llama.cpp b12340 adds CUDA 13 and ROCm 10.0
This release quietly closes the hardware gap for local inference by adding default support for CUDA 13 and ROCm 10.0 across Linux and Windows. Users with newer NVIDIA GPUs or AMD accelerators no longer need to compile from source to get performance, while Apple Silicon builds now ship KleidiAI disabled by default, shifting the focus back to standard ARM optimizations. The inclusion of Snapdragon support for Linux and Android marks a significant step toward on-device AI beyond the x86/ARM desktop ecosystem. It is less about new features and more about ensuring llama.cpp remains the universal runtime for every available accelerator.
llama.cpp Releases
Models & Labscoding
llama.cpp b12342 adds few-row MMQ for speculative decoding
Speculative decoding just got a significant speed boost on NVIDIA GPUs. This release introduces a specialized kernel for 'few-row' matrix multiplications, targeting the small batch sizes typical of verification passes in speculative decoding workflows. By optimizing these specific operations for quantized formats like Q8_0 and IQ4 variants, llama.cpp reduces latency where it matters most during token generation. The change is CUDA-only for now but leverages hardware capabilities from Ampere onwards, making local inference faster without requiring new model architectures or complex configuration changes.
llama.cpp Releases
© TechCrunch AIModels & Labsmodels
Google deploys Gemini 4 Hydrogen for faster Search
Google is quietly shifting its search infrastructure by replacing older fast models with Gemini 4 Hydrogen, a tier designed specifically for speed and cost-efficiency rather than raw reasoning power. This model completes tasks 2.5 times faster than its predecessor while beating the more powerful Argon on specific intelligence benchmarks, proving that specialized efficiency can outperform brute force in high-volume workflows. By integrating this into Search's fan-out technique, Google now breaks down complex queries into subqueries with greater precision and speed, delivering richer visual responses without the latency of heavier models. This marks a strategic pivot toward agentic execution layers within consumer search, making AI Mode feel snappier for everyday multi-part questions.
TechCrunch AI