Nine coding harnesses vs. your laptop

humbleferret•7 minutes ago

Nice writeup! I imagine these results change as harnesses are updated, so you'd need to frequently rereview.

I'd love to see a tiny, reproducible benchmark repo that anyone can drop on their own hardware and then run against all harnesses at once to compare the per turn prefix token count, time to the first token, experienced tokens/sec (and prefill), cache reuse % and a pass rate on a deterministic set of small tasks. I think it could also be useful to have some way to share results and hardware for others to compare.

OleksandrC•about 1 hour ago

If you're looking for a coding agent that would fit nicely into resource-constrained environments (such as laptops, or tiny VPS servers, or tiny single-board computers, etc), and would also work great with local models - you might also like hax (https://usehax.dev/). 0.7 MB dynamically linked native C binary, few MBs of RAM usage when running, auto-discovers config from running local llama-server, and uses minimalist system prompt and tools for lean context usage.

mischief6•40 minutes ago

ive looked at your project before but forgot about it. I think mine is in a similar vein: https://github.com/mischief/clm

it grew out of annoyance of dependencies on js runtimes, probably similar to you. mine additionally works on solaris and esp32.

could be interesting to collaborate!

toasty228•36 minutes ago

A bit off topic because I'm not using local models, but I recently benchmarked codex vs pi vs omp with my workload and found codex to be both faster and more token efficient than pi/omp. There was not a single case for which pi was faster/cheaper

alex_john_m•about 2 hours ago

What is this supposed to mean?

"it spreads up to 50% between nights, so nothing between the lean arms is a finding."

entrope•about 2 hours ago

The same thing as the last word of "That is the difference between 22 and 226 seconds, measured." Techies I know would mostly omit "measured"; the rest would show, not tell.

stavros•about 1 hour ago

Means Claude can't write for shit.

ramon156•4 minutes ago

Or chad

tontinton•about 1 hour ago

I've made https://maki.sh for use cases such as this

teekert•about 2 hours ago

Fun reference I tested on 32 GB ram laptop with no extra GPU: llama.cpp: “what is ls”, almost immediate starts answering at one ~word/sec. Ask opencode with same model (some gwen e4b or something) to check what’s in its working directory: 20 min to response.

throwa356262•about 1 hour ago

Opencode system prompt contains a lot of stuff but even worse is oh-my-pi where their long prompt looks like random garbage hallucinated by a 2023 LLM:

https://m.youtube.com/watch?v=c_fQoDkULl0 (see around 8:00)

montyanne•about 2 hours ago

Neat article.

“Chad” initially looked interesting but the minute I saw the ai-written markdown and giant commit I just left. I just can’t bring myself to read someone elses’ slop, regardless of performance.

If all a developer hand writes is a truthy and readable markdown document, I really don’t care if the rest of the project is vibe coded, but I struggle to get interested in AI generated summaries and docs.

CGamesPlay•about 2 hours ago

I for one am excited to learn more about how it spreads up to 50% between nights, and how nothing between the lean arms is a finding.

ramon156•3 minutes ago

Don't forget it's, measured.

NooneAtAll3•about 1 hour ago

wtf is wrong with scrolling on that website?

Nine coding harnesses vs. your laptop

⚡ Community Insights

Discussion (15 Comments)Read Original on HackerNews