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

Orchestrate teams of Claude Code sessions

code.claude.com

Post reply on HN
Print view View original

161–170 of 238 posts

Re: Orchestrate teams of Claude Code sessions

#161

Post by MattPalmer1086 »

gbnwl wrote: post #124
mohsen1 wrote: post #98

Earlier quoted context omitted.

It's not like he was the only one who came up with this idea. I built something like that without knowing about GasTown or Beeds. It's just an obvious next step https://github.com/mohsen1/claude-code-orchestrator

I also share your confusion about him somehow managing to dominate credit in this space, when it doesn't even seem like Gastown ended up being very effective as a tool relative to its insane token usage. Everyone who's used an agentic tool for longer than a day will have had the natural desire for them to communicate and coordinate across context windows effectively. I'm guessing he just wrote the punchiest article a…

It was a fun article!

Re: Orchestrate teams of Claude Code sessions

#162

Post by bethekidyouwant »

resonious wrote: post #122
frde_me wrote: post #119

Earlier quoted context omitted.

It's hard to explain, but I've found LLMs to be significantly better in the "review" stage than the implementation stage. So the LLM will do something and not catch at all that it did it badly. But the same LLM asked to review against the same starting requirement will catch the problem almost always The missing thing in these tools is that automatic feedback loop between the two LLMs: one in review mode, one in impl…

I've noticed this too and am wondering why this hasn't been baked into the popular agents yet. Or maybe it has and it just hasn't panned out?

You have to dump the context window for the review to work good.

Re: Orchestrate teams of Claude Code sessions

#163

Post by freeone3000 »

rahimnathwani wrote: post #139
freeone3000 wrote: post #134

Earlier quoted context omitted.

If it could do anything that a junior dev could, that’d be a valid point of comparison. But it continually, wildly performs slower and falls short every time I’ve tried.

But it continually, wildly performs slower and falls short every time I’ve tried. If it falls short every time you've tried, it's likely that one or more of these is true: A. You're working on some really deep thing that only world-class expects can do, like optimizing graphics engines for AAA games. B. You're using a language that isn't in the top ~10 most popular in AI models' training sets. C. You have an opportun…

It’s a simple compiler optimization over bayesian statistics. It’s masters-level stuff at best, given that I’m on it instead of some expert. The codebase is mixed python and rust, neither of which are uncommon.

The issues I ran into are primarily “tail-chasing” ones - it gets into some attractor that doesn’t suit the test case and fails to find its way out. I re-benchmark every few months, but so far none of the frontier models have been able to make changes that have solved the issue without bloating the codebase and failing the perf tests.

It’s fine for some boilerplate dedup or spinning up some web api or whatever, but it’s still not suitable for serious work.

Re: Orchestrate teams of Claude Code sessions

#164

Post by rahimnathwani »

freeone3000 wrote: post #163
rahimnathwani wrote: post #139

Earlier quoted context omitted.

But it continually, wildly performs slower and falls short every time I’ve tried. If it falls short every time you've tried, it's likely that one or more of these is true: A. You're working on some really deep thing that only world-class expects can do, like optimizing graphics engines for AAA games. B. You're using a language that isn't in the top ~10 most popular in AI models' training sets. C. You have an opportun…

It’s a simple compiler optimization over bayesian statistics. It’s masters-level stuff at best, given that I’m on it instead of some expert. The codebase is mixed python and rust, neither of which are uncommon. The issues I ran into are primarily “tail-chasing” ones - it gets into some attractor that doesn’t suit the test case and fails to find its way out. I re-benchmark every few months, but so far none of the fron…

Would you expect a junior engineer to perform better than this?

Re: Orchestrate teams of Claude Code sessions

#165

Post by __turbobrew__ »

dangus wrote: post #136
logicx24 wrote: post #131

Earlier quoted context omitted.

I can't even get through my Claude Max quota, and that's only 200/mo. And I code every day and use it for various other pretty-intensive tasks.

only $200/mo… $200 a month is a used car payment. I guarantee you that price will double by 2027. Then it’ll be a new car payment! I’m really not saying this to be snarky, I’m saying this to point out that we’re really already in the enshittification phase before the rapid growth phase has even ended. You’re paying $200 and acting like that’s a cheap SaaS product for an individual. I pay less for Autocad products! Th…

$200/month is peanuts when you are a business paying your employees $200k/year. I think LLMs make me at least 10% more effective and therefore the cost to my employer is very worth it. Lots of trades have much more expensive tools (including cars).

Re: Orchestrate teams of Claude Code sessions

#166

Post by __turbobrew__ »

rune-dev wrote: post #149
nlh wrote: post #143

Earlier quoted context omitted.

I pay $200/month, don’t come near the limits (yet), and if they raised the price to $1000/month for the exact same product I’d gladly pay it this afternoon (Don’t quote me on this Anthropic!) If you’re not able to get US$thousands out of these models right now either your expectations are too high or your usage is too low, but as a small business owner and part/most-time SWE, the pricing is a rounding error on value…

As a business expense to make profit, I can understand being ok with this price point. But as an individual with no profit motive, no way. I use these products at work, but not as much personally because of the bill. And even if I decided I wanted to pursue a for profit side project I’d have to validate it’s viability before even considering a 200$ monthly subscription

Some tools are not meant for individuals. That 100k software defined radio isn’t meant for you either.

Re: Orchestrate teams of Claude Code sessions

#167

Post by dangus »

nlh wrote: post #143
dangus wrote: post #136

Earlier quoted context omitted.

only $200/mo… $200 a month is a used car payment. I guarantee you that price will double by 2027. Then it’ll be a new car payment! I’m really not saying this to be snarky, I’m saying this to point out that we’re really already in the enshittification phase before the rapid growth phase has even ended. You’re paying $200 and acting like that’s a cheap SaaS product for an individual. I pay less for Autocad products! Th…

I pay $200/month, don’t come near the limits (yet), and if they raised the price to $1000/month for the exact same product I’d gladly pay it this afternoon (Don’t quote me on this Anthropic!) If you’re not able to get US$thousands out of these models right now either your expectations are too high or your usage is too low, but as a small business owner and part/most-time SWE, the pricing is a rounding error on value…

"Rounding error" lol, you can hire an actual full time human in India for $1000/month.

Re: Orchestrate teams of Claude Code sessions

#168

Post by bdangubic »

dangus wrote: post #167
nlh wrote: post #143

Earlier quoted context omitted.

I pay $200/month, don’t come near the limits (yet), and if they raised the price to $1000/month for the exact same product I’d gladly pay it this afternoon (Don’t quote me on this Anthropic!) If you’re not able to get US$thousands out of these models right now either your expectations are too high or your usage is too low, but as a small business owner and part/most-time SWE, the pricing is a rounding error on value…

"Rounding error" lol, you can hire an actual full time human in India for $1000/month.

wouldn’t hire one for $15/month…

with the US salaries for SWEs $1000/month is not a rounding error for all but definitely for some. say you make $100/hr and CC saves you say 30hrs / month? not rounding error but no brainer. if you make $200+/hr it starts to become a rounding error. I have multiple max accounts at my disposal and at this point would for sure pay $1000/month for max plan. it comes down to simple math

Re: Orchestrate teams of Claude Code sessions

#169

Post by dangus »

meowface wrote: post #141
dangus wrote: post #136

Earlier quoted context omitted.

only $200/mo… $200 a month is a used car payment. I guarantee you that price will double by 2027. Then it’ll be a new car payment! I’m really not saying this to be snarky, I’m saying this to point out that we’re really already in the enshittification phase before the rapid growth phase has even ended. You’re paying $200 and acting like that’s a cheap SaaS product for an individual. I pay less for Autocad products! Th…

I could write an essay about how almost everything you wrote either is extremely incorrect or is extremely likely to be incorrect. I am too lazy to, though, so I will just have to wait for another commenter to do the equivalent.

Why not make your AI tool do it for you?

Re: Orchestrate teams of Claude Code sessions

#170

Post by dangus »

__turbobrew__ wrote: post #165
dangus wrote: post #136

Earlier quoted context omitted.

only $200/mo… $200 a month is a used car payment. I guarantee you that price will double by 2027. Then it’ll be a new car payment! I’m really not saying this to be snarky, I’m saying this to point out that we’re really already in the enshittification phase before the rapid growth phase has even ended. You’re paying $200 and acting like that’s a cheap SaaS product for an individual. I pay less for Autocad products! Th…

$200/month is peanuts when you are a business paying your employees $200k/year. I think LLMs make me at least 10% more effective and therefore the cost to my employer is very worth it. Lots of trades have much more expensive tools (including cars).

> I think LLMs make me at least 10% more effective

I know this was last year but...

https://metr.org/blog/2025-07-10-early-2025-ai-experienced-o...

Post reply on HN