HackerTrans
TopNewTrendsCommentsPastAskShowJobs

tontinton

no profile record

Submissions

[untitled]

1 points·by tontinton·قبل 28 يومًا·0 comments

[untitled]

1 points·by tontinton·قبل 3 أشهر·0 comments

[untitled]

1 points·by tontinton·قبل 3 أشهر·0 comments

[untitled]

1 points·by tontinton·قبل 3 أشهر·0 comments

[untitled]

1 points·by tontinton·قبل 3 أشهر·0 comments

[untitled]

1 points·by tontinton·قبل 3 أشهر·0 comments

[untitled]

1 points·by tontinton·قبل 3 أشهر·0 comments

Maki the efficient AI coder – Rust TUI (saves 40% tokens and low RAM)

maki.sh
5 points·by tontinton·قبل 3 أشهر·1 comments

Lance table format explained simply, stupid (Animated)

tontinton.com
16 points·by tontinton·قبل 5 أشهر·6 comments

I added partial (incomplete) row streaming to a query engine

blog.vega.io
1 points·by tontinton·قبل 6 أشهر·0 comments

Partial Streams: Real-Time Results in a Federated Query Engine

blog.vega.io
4 points·by tontinton·قبل 9 أشهر·0 comments

comments

tontinton
·قبل 15 يومًا·discuss
Yep this is a glimpse into the future of 500+ t/s, which is in my opinion the next big thing that validates Jevon's paradox (the models are already smart enough)
tontinton
·قبل 22 يومًا·discuss
I meant harnesses / TUIs, sorry to confuse.

Using fd/rg sounds interesting, honestly it would require little tweaks to the bash tool lua plugin, either add to the description to prefer these binaries instead or something like that.

In general though I much prefer "advising" and encouraging the LLM to use the native tools like grep l/glob, they are implemented to be super fast, and you will get better parser output.
tontinton
·قبل 22 يومًا·discuss
Create an issue! :)
tontinton
·قبل 22 يومًا·discuss
It's a TUI you're right, but it's also a harness.

As much as I hate to admit, T the tools you provide, the descriptions, and prompts, all amount to pretty big changes in experience, even using the same models.
tontinton
·قبل 23 يومًا·discuss
The biggest ones are: using tree-sitter to index code files as a tool, code_execution tool running a workflow of tools inside a python interpreter (monty), and not being a harness developed by the company profiting from selling you the shovels (and introducing "dynamic workflows" aka spawning 50 agents).
tontinton
·قبل 23 يومًا·discuss
Enjoy, I can't go back to other agents now, too spoiled by the speed
tontinton
·قبل 23 يومًا·discuss
Totally wrong, you underestimate the frontier's incompetence in anything other than building LLM models (ehm ehm flickering TUI for a year "written like a game engine").

I ran a bunch of benchmarks and there are proven ways to reduce tokens while achieving the same results (finding the same CVEs / finding the same bugs in CRs, etc...).

See https://maki.sh, it's my own little proof.
tontinton
·قبل شهرين·discuss
Yep exactly my thoughts, went and looked at the code for the deepseek provider in my coding agent. and basically all of what the author wrote there is implemented... http://github.com/tontinton/maki for the curios
tontinton
·قبل شهرين·discuss
What's your moat?
tontinton
·قبل شهرين·discuss
Yo that's really similar to my very own https://github.com/tontinton/maki only I'm MIT and you're GPL, cool
tontinton
·قبل شهرين·discuss
Also easier to ship a binary like a cli
tontinton
·قبل 3 أشهر·discuss
or you can use a non vibe designed efficient Rust TUI coding agent made by yours truly, all my coworkers use it too :) called https://maki.sh!

lua plugins WIP
tontinton
·قبل 3 أشهر·discuss
Thanks!

Currently the subagent chat windows don't allow to inject user messages like the main window, I want to change that soon though.

Regarding tiered models, it currently caps the model use to the current tier you're on, so no it can't upgrade from haiku to opus suddenly. The reasoning for that is that if you selected haiku, you probably don't want to pay for opus by accident.
tontinton
·قبل 3 أشهر·discuss
Yes, you can use the dynamic provider to work with any local model you want (see scripts/providers)
tontinton
·قبل 3 أشهر·discuss
Is this a good time to tell you guys that there are many more alternatives, like my very own https://maki.sh?

Shameless plug, yes, but it's free, so I think it's fair :)
tontinton
·قبل 3 أشهر·discuss
I don't know why everyone is so attached to Claude Code you can just build your own little agent, like I did: https://maki.sh/

It will 100% be better than the 500k lines of code junk that is CC.
tontinton
·قبل 3 أشهر·discuss
Something I've been working on out of frustrations with the existing AI coder CLIs
tontinton
·قبل 3 أشهر·discuss
[flagged]
tontinton
·قبل 4 أشهر·discuss
Yeah we all converge to the same workflow, in my ai coding agent I'm working on now, I've added an "index" tool that uses tree-sitter to compress and show the AI a skeleton of a code file.

Here's the implementation for the interested: https://github.com/tontinton/maki/blob/main/maki-code-index%...
tontinton
·قبل 4 أشهر·discuss
Is it similar to rtk? Where the output of tool calls is compressed? Or does it actively compress your history once in a while?

If it's the latter, then users will pay for the entire history of tokens since the change uncached: https://platform.claude.com/docs/en/build-with-claude/prompt...

How is this better?