
What DeepSeek's Open-Source Agent Harness Gets Right
A few weeks ago, my dad and I spent an afternoon at the kitchen table trying to figure out what an "AI agent" actually is.
Subscribe to Lê Đức Minh's Newsletter
Get new articles and engineering posts delivered to your inbox.

A few weeks ago, my dad and I spent an afternoon at the kitchen table trying to figure out what an "AI agent" actually is.

State‑of‑the‑art LLMs, even Vietnamese‑specialized ones, score below 50 % on the VIVID benchmark of 1,636 authentic Vietnamese idioms and fa...

Benchmark reveals Llama-3.1-8B mislabels Vietnamese slang as angry, losing 20 F1 points, while three other LLMs correctly interpret social m...

Discover why Vietnamese tokenizers cost only 1.05‑2.14× English tokens, not 4.5×, and how updating tokenizers can cut LLM expenses by a thir...

TokPress compresses tiny JSON log lines by tokenizing with OpenAI's o200k_base tokenizer, then applying LZ77 and rANS for smaller files.

TokPress compresses tiny JSON log lines by tokenizing with OpenAI's o200k_base tokenizer, then applying LZ77 and rANS for smaller files.

Field notes from a weekend spent teaching an entropy coder to speak LLM. LLMs spent billions of dollars learning the best subword dictionary...

In July I wrote Prompt, Context, Harness, Loop, which split an agent into four parts and argued that the harness — the thing that owns the l...

Part 2 of 2 on prompt caching. Part 1 covered the economics. Part 1 established the prize: caching cut an 80-turn agent session from $54.08 ...

Part 1 of 2 on prompt caching. I got curious about a number I had never actually checked: what does a long session with a coding agent reall...

Field notes, part 1 of 3. Data plumbing from an AI engineer's desk.* My job title says AI. A meaningful share of my week is data. Not the gl...