Why Use Many Word When Few Word Do Trick: Optimising Claude Code Token Usage
Claude Code token usage does go down if you use fewer words. Just not by much in most real sessions….
-
-
Claude Code Reasoning Effort Fell, and Quality Followed
Anthropic says the Claude Code reasoning effort default was lowered from high to medium in early March to reduce latency,…
-
Product Tutorial Videos Now Update Themselves
Product tutorial videos used to be a small production project: record the screen, write the script, clean up the narration,…
-
Claude Opus 4.7 Token Usage Jumped 35% Without Price Hikes
Claude Opus 4.7 token usage went up for reasons Anthropic documented in its own launch materials. The list price stayed…
-
Claude Opus 4.6 Support: Docs Say Active, UI Says No
Claude Opus 4.6 support has not been formally dropped. Anthropic’s model deprecations page still lists claude-opus-4-6 as Active and says…
-
Kimi K2.6 Rewrote Legacy Code for 185% More Throughput
Kimi K2.6 is an open-source coding model release from Moonshot AI, published on April 20, 2026. According to Moonshot’s release…
-
Speculative Checkpointing Pays Off Only on Repetitive Text
In llama.cpp, speculative checkpointing matters for a simple reason: it points local users toward a cheaper speculative path. You can…
-
Focused Ultrasound Turns Smell-In-VR Into a Brain Problem
A small research team says focused ultrasound can make people perceive smells without releasing any chemicals at all. If that…
-
AI Video Generation Works for Trailers, Not Feature Films
I tried watching the latest wave of AI video generation demos the way a studio exec or ad creative would:…
