Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

The Harness Is the Thing

scott-fryxell.github.io

Post reply on HN
Print view View original

71–80 of 95 posts

Re: The Harness Is the Thing

#71

Post by ghthor »

all2 wrote: post #4
AirMax98 wrote: post #3

Reading this really makes me wish that I had a slightly better workflow. I'm really soley dependent of Fable to the point that I don't use other models, and I've already sort of hit a point where I'm running into usage limits every week. I am really living on borrowed time — when Anthropic finally collapses their 50% usage increase at the end of August, I'll definitely be forced to switch my workflow. When that happe…

I've been using GPT-5.6 Luna for everything at this point. It is more than enough to do all the work I need to do. You have to lead it by the nose, but if you know where you're going it works really, really well.

Same, all I need is speed to execute editing faster than I could in vim. Luna is cheap, intelligent enough, and fast enough I don’t lose the sense of flow.

Re: The Harness Is the Thing

#72

Post by _0ffh »

adverbly wrote: post #69
andunie wrote: post #65

I don't understand why no one has tried to make a harness without full shell access yet. It would be so much safer.

sandboxing?

That's what I though. I've got a harness that uses landlock. Might not be perfect, but should be good enough for almost all cases.

Re: The Harness Is the Thing

#73

Post by skohan »

esalman wrote: post #23

What I've learned in last week is that a harness is basically a while loop. In each iteration you make an LLM call, perform some work (e.g. tool call), augment the prompt (append or compact etc.)- not necessarily in that other- and continue. Until an end condition is satisfied. Then you break out.

That's the most basic version of a harness. But a harness is really about automating context delivery to the LLM based on your use-case.

Re: The Harness Is the Thing

#74

Post by skohan »

adverbly wrote: post #70
skohan wrote: post #68

Earlier quoted context omitted.

Is that the harness' job? It seems to me the best place for sandboxing is at the OS level (i.e. running the harness inside a container with correct access configured).

I would argue that it is the harness's job... Certainly for any harness which is targeting an end user. They don't sell cars without seat belts, and it is the car manufacturer who has to do it. Also, small nitpick but technically a container doesn't give full isolation compared to something like a VM.

Ok that's fair if it's targeting a non-technical audience.

But I think this will eventually be a problem solved at the OS level in a more streamlined way. I.e. there will be fine-grained permissions you need to approve to give an agent access to the system.

Re: The Harness Is the Thing

#75

Post by vidarh »

jwrallie wrote: post #11
all2 wrote: post #4

Earlier quoted context omitted.

I've been using GPT-5.6 Luna for everything at this point. It is more than enough to do all the work I need to do. You have to lead it by the nose, but if you know where you're going it works really, really well.

It seems there are two distinct groups, one which is doing relatively well with Luna, Deepseek Flash and similar models while other seem to be satisfied only with the state of the art.

GP kinda explains why: "You have to lead it by the nose".

If you're happy to "lead it by the nose" you can do well with a lot of very low end models.

If you want to kick off a "/goal run until [complex verification passes]" and let it run for a week with minimal intervention, then not so much.

You can make do with cheaper models for long running agentic runs too, but it tends to require a lot of extra scaffolding and additional review steps.

Re: The Harness Is the Thing

#76

Post by dmantis »

> Single developer projects can build to the caliber and consistency of large development teams.

Yet the simple blog website static page saying that looks very weird and broken on the desktop firefox.

How large should be a development team to make proper margins in 2026?

Re: The Harness Is the Thing

#78

Post by KronisLV »

AirMax98 wrote: post #3

Reading this really makes me wish that I had a slightly better workflow. I'm really soley dependent of Fable to the point that I don't use other models, and I've already sort of hit a point where I'm running into usage limits every week. I am really living on borrowed time — when Anthropic finally collapses their 50% usage increase at the end of August, I'll definitely be forced to switch my workflow. When that happe…

> when Anthropic finally collapses their 50% usage increase at the end of August, I'll definitely be forced to switch my workflow

I cancelled my Anthropic subscription until they fix how their models write and it's no longer unbearably annoying and obnoxious. The concise output format is a step in the right direction but I need a few months away from them.

Kimi and GLM models on Max reasoning feel pretty close to Fable. That said, even at their most expensive plans, a single one of them might not always be enough, while getting both of them for a year gives you a nice discount and isn't insanely more expensive than Anthropic. The problem there is that they could still easily rugpull you with token limit changes later, I don't trust any of the big labs not to mess around with those for any length of time.

Also most harnesses let you choose models per sub-agent. Like I can use Fable for running the main session and just tell it to use Opus agents for implementation in Claude Code, same with the Kimi and GLM models inside of OpenCode and other harnesses. The only problem is that the UI for controlling sub-agents usually really sucks.

Re: The Harness Is the Thing

#79

Post by noir_lord »

dmantis wrote: post #76

> Single developer projects can build to the caliber and consistency of large development teams. Yet the simple blog website static page saying that looks very weird and broken on the desktop firefox. How large should be a development team to make proper margins in 2026?

I was a little "what a weird nitpick" then I opened it on FF and yeah... that's awful.

Normally I'd just switch into FF reader view when it's that badly done but that doesn't work either.

Re: The Harness Is the Thing

#80

Post by appplication »

KronisLV wrote: post #78
AirMax98 wrote: post #3

Reading this really makes me wish that I had a slightly better workflow. I'm really soley dependent of Fable to the point that I don't use other models, and I've already sort of hit a point where I'm running into usage limits every week. I am really living on borrowed time — when Anthropic finally collapses their 50% usage increase at the end of August, I'll definitely be forced to switch my workflow. When that happe…

> when Anthropic finally collapses their 50% usage increase at the end of August, I'll definitely be forced to switch my workflow I cancelled my Anthropic subscription until they fix how their models write and it's no longer unbearably annoying and obnoxious. The concise output format is a step in the right direction but I need a few months away from them. Kimi and GLM models on Max reasoning feel pretty close to Fab…

Yes both Opus and Fable’s comment style is truly unbearable. I like the code result but it’s so annoying seeing it reflect our conversation as code comments.
Post reply on HN