AI Brain Fry: What BCG Found in 1,488 Workers
AI brain fry hit 14% of AI-using workers in the BCG-Harvard study. Devs near the top, behind marketing and HR. Productivity drops once you cross 4 tools.
Posts
4.7x Faster Long-Context LLM Inference: AsyncTLS Explained
Long-context LLM inference collapses past 96k tokens. AsyncTLS pairs two-level sparse attention with async KV offloading for 1.3-4.7x more throughput.
Cursor Composer 2 Review: Cheaper Than Opus, Built on Kimi K2.5
Cursor Composer 2 ships at $0.50/M input — roughly 1/10 of Opus 4.6 — and beats Opus on Terminal-Bench. Then a developer found Kimi K2.5 in the model ID.
Go Iterators in Practice: iter.Seq, Seq2, Pull, and Zip
Go iterators with iter.Seq and Seq2: the yield contract, early exit without a runtime panic, zipping two sequences with iter.Pull, and its 30x per-element cost.
Cyprus Software Engineer Salary 2026: What You'll Actually Earn in Limassol and Nicosia
Cyprus software engineer salary 2026 — real levels.fyi numbers for Limassol vs Nicosia, plus how the new 50% exemption above €55K flips net pay vs Berlin.
Claude Code Subagents: The Practical Guide
Claude Code subagents run side tasks in their own context window. Here's how to create them, when to pick one over a skill, and the mistakes to avoid.
Recursive Language Models (RLMs): How MIT's REPL Trick Handles 11M-Token Prompts
Recursive language models keep a huge prompt in a Python REPL and recurse over the pieces. RLM(GPT-5) scores 91.3 on 6M-11M-token inputs plain GPT-5 can't fit.
Agentic Memory: The Paper That Teaches LLMs to Manage Their Own Memory
A new paper from Alibaba teaches LLM agents to store, update, and delete their own memory via reinforcement learning. Beats Mem0 and A-Mem on 5 benchmarks.
Polars vs Pandas in 2026: Performance Benchmarks, Real Numbers, and When to Switch
Polars vs Pandas in 2026: independent benchmarks show 7-40x speedups on large data. What Pandas 3.0 fixes, and what still favors Polars.
mypy vs Pyright vs ty: Python Type Checker Comparison (2026)
mypy vs Pyright vs ty: speed, conformance and IDE support. Pyright leads at 98% spec conformance; ty is 10-60x faster but passes only 53% of tests.