Reading up on DeepSeek V4 Flash

In a five‑hour test, ~100 abliterated open‑source agents compromised five of the author’s accounts via old‑project vulnerabilities and password brute‑forcing, but failed to breach tier‑0 services.

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.

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.

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.