Viewing profile — bonigv

TL;DR; You can save ~50-60% context tokens spent in exploration w/o compromising quality by delegating exploration to a local LLM. The cost is the execution time. Which can vary de…

You are absolutely right about what we feel intuitively - LSPs should beat the shit out of the competition. But surprisingly it did not. Across 10 different LSP servers, across 5 d…

oh! I thought this was like bash w/o verbosity. That is a tool I would love to see. bash4llm . May be llike Gandhi said - I should be the change you want to see!

[flagged]

Felt LSP Servers were too complex. Bash tools alone too brutish. Wanted to see what if it is a tree-sitter as a firstclass tool. Ran a bench over 10 large codebases [bitcoin, djang…

Bruno, if we are operating the agent (assuming coding-agent ) in an environment where the build and test tools as well the source code lives, why would we need an additional step t…

Agree. The challenge is that same model/provider can use dramatically different numbers for thefirst two items. Maintainability is an invariant of quality of the system. Measuring …

Agree that LOC and Story points are not metrics that needs tracking. What is happening is that same model and provider can use a very different experience in terms of [Turns, Token…

A bit of a rant. Sorry! With the probablistic pluggable 'brain' existing in parts of the solution how are you measuring anything is better or worse? I am at a loss to quantify whet…

Lots of products working on saving-tokens-space. Compression, Tool Output rewrite, Sitting as proxy Cache between harness and provider , doing circus with interceptor hooks - these…

This is a fascinating thought. I agree. It is one thing to let it write a prompt. Prompting, Generating, Judging and going till it is satiated is gluttony. Every week I ship 4-5 sp…

[dead]

Clarifying - I am not suggesting headroom and lean-ctx are only doing the tool compression. It runs elaborate subsystems towards a noble objective of saving tokens. RTK on the othe…

Many projects and addons exists to reduce the verbosity on standard bash / git /npm etc. Commands that agents pass regularly as tools to LLMs. (eg. rtk, headroom, lean-ctx). Tool o…

[dead]

It is a very valid question. My intution (no grounding) is to the model training. Optimizations traditionally have worked well in human wrote software with either experience of the…

[flagged]

[dead]

[dead]