Tag
LLM
5 articles
Claude Opus 4.7: Anthropic's New Flagship Clears SWE-Bench Pro
Anthropic's Opus 4.7 hits 64.3% on SWE-bench Pro, adds an xhigh effort level, and ships with 3x sharper vision. But the new tokenizer quietly shifts your bill, and Mythos still sits in the drawer.
By Sarah Chen · 6 min · Apr 19, 2026
AI NewsQwen 3.6 Plus: Alibaba's Free Preview Beats Claude Opus on Agent Tasks
Alibaba's Qwen 3.6 Plus Preview posts 61.6 on Terminal-Bench 2.0, runs at 158 tok/s, and ships with a 1M-token context window — all free during the preview window.
By Sarah Chen · 5 min · Apr 15, 2026
Tech TipsCaveman: The Claude Code Skill That Cuts 65% of Output Tokens
Caveman makes Claude talk like a caveman and cuts output tokens by 65% on average. 30,400 GitHub stars, MIT licensed, and one install command across every major AI agent.
By Marcus Rivera · 5 min · Apr 15, 2026
Tech TipsEdgee Codex Compressor: The Rust Gateway That Cuts Codex Costs 35.6%
Edgee is an Apache 2.0 Rust LLM gateway that compresses tool output before it hits the model — cutting Codex session costs by 35.6% with no code changes.
By Marcus Rivera · 4 min · Apr 12, 2026
GPT-5.4: OpenAI's Five-Variant Strategy Reshapes the AI Market
OpenAI releases GPT-5.4 in five variants with native computer use surpassing human experts and a new Tool Search architecture for agent systems.
By Sarah Chen · 5 min · Mar 29, 2026