131–140 of 318 posts
https://github.com/jahala/tilth
its on npm and cargo:
- cargo install tilth
- npx tilth
then tilth install claude-code/windsurf/cursor --edit
(--edit flag is needed)
I made "tilth" a few days ago, since I'm consistently trying to get the LLMs to use tools more efficiently and spend less tokens doing it -- original tilth post from Monday: https://news.ycombinator.com/item?id=46952321
On first principles it would seem that the "harness" is a myth. Surely a model like Opus 4.6/Codex 5.3 which can reason about complex functions and data flows across many files would trip up over top level function signatures it needs to call? I see a lot of evidence to the contrary though. Anyone know what the underlying issue here is?
Arguably I would think that the last year was mainly inner harness improvement instead model improvement but I could be wrong, just feels like that to me
Models have improved dramatically even with the same harness
I implemented this hash (read and edit) approach in tilth if you want to test it out. https://github.com/jahala/tilth its on npm and cargo: - cargo install tilth - npx tilth then tilth install claude-code/windsurf/cursor --edit (--edit flag is needed) I made "tilth" a few days ago, since I'm consistently trying to get the LLMs to use tools more efficiently and spend less tokens doing it -- original tilth post from Mo…
Putting it out there: if any frontier model provider starts allowing any agent to use their $20/month plan, we will all switch to you. We don't want to be forced into 1 harness, we want OAuth, and we want respectable limits without excessive budgets.
On first principles it would seem that the "harness" is a myth. Surely a model like Opus 4.6/Codex 5.3 which can reason about complex functions and data flows across many files would trip up over top level function signatures it needs to call? I see a lot of evidence to the contrary though. Anyone know what the underlying issue here is?
Earlier quoted context omitted.
Because I like them?
how do you make them?
During my first LLM experiments in Emacs using gptel, I also found that the LLM has considerable difficulties changing source code files with the Unix patch tool. As Emacs has a built-in tree-sitter package, I implemented this same idea. I created gptel tools like tree_sitter_list_nodes, tree_sitter_get_nodes, tree_sitter_update_nodes, tree_sitter_insert_before_node and tree_sitter_insert_after_node. The "list" tool…
Sounds interesting, do you have the code to share.
Implementation: https://github.com/cellux/dotfiles/blob/master/.emacs.d/rb-t...