Thread

1. stratos123 · 1789498322 · focus · HN ↗

   The writing is slop. It doesn't mention a detail I have seen people actually not get: that LLMs wrap tool calls in special tokens, so they are "out of band" and can't be mistaken with normal output.

   It also spends an entire section trying to convey that large tools waste tokens:

     A read_file that returns an 8k-token source file on turn 2 of a ten-turn agent gets resent on the eight requests that follow: 8 × 8k = +64k input tokens, $0.32, from one tool result.
   

   but surely that's wrong - it's part of the same conversation, it only gets processed once and then cached. Otherwise doing long conversations would always cost an amount quadratic with length.

   1. dvt · 1789499055 · focus · HN ↗

      > I have seen people actually not get: that LLMs wrap tool calls in special tokens

      This isn't necessarily true. I'm working on a local harness that doesn't do this and instead coerces everything to YAML (including tool calls) for better bucketing. Some models are indeed trained on the `<|tool_call>...<tool_call|>` token schema (or something similar—e.g. jinja), but it's vendor-specific and often times inconsistent (so you're constantly fixing calls or going back to the LLM).

      1. stephenblum · 1789501777 · focus · HN ↗

         nice! like HTML tags. I remember seeing this back with meta Llama 2. the <|start_header_id|>assistant<|end_header_id|> style. And [TOOL_CALLS] ... [/TOOL_CALLS] style with Mistral

Unofficial Hacker News client; not affiliated with Y Combinator.