I Tried to Make AI Writing Sound Human by Banning AI Words Through logit_bias - Vincent Schmalbach

kept by eddie jul 30

The author applied logit_bias to penalize AI‑common tokens, observing a roughly one‑third reduction in those words while sacrificing one acceptable rewrite out of eight.

How does AI impact skill formation?
A 2025 Anthropic study shows AI-assisted coding can reduce skill retention but 25% speed boost emerges when ignoring participants who manually retyped AI code.
also on GPT-4o, Anthropic, #ai-coding, #software-engineering, #developer-tools
The Problem is Prompt Debt
Hand-tuning natural language prompts for AI systems accumulates debt that slows iteration, locks teams to one model, and should be replaced with metrics, tests, and automated prompt optimization.
also on GPT-4o, #software-engineering, #ai, #developer-tools
The machine never raises its voice
LLMs consistently prefer their own machine-generated literary passages over human-authored classics, valuing precision and restraint over voice and strangeness when evaluating literary quality.
also on DeepSeek V4 Flash, #software-engineering, #ai, #developer-tools
AI At Home Part 2: Multi GPU Drifting
The author boosted Deepseek V4 Flash inference from ~10 to ~20 tokens/sec on four e-waste AMD V620 GPUs by using layer parallelism and a speculative draft model.
also on DeepSeek V4 Flash, #ai-coding, #developer-tools
Do All Your Agents Really Need Models Like Claude 5 or GPT-5.6?
Many AI agent tasks don't need frontier models; matching model capability to task complexity can cut costs by up to 75%.
also on GPT-5.6 Sol, Claude, Anthropic, #ai, #developer-tools