Comments URL: https://news.ycombinator.com/item?id=48952646

Points: 1

# Comments: 0

No they're not. It would end both companies if they were ever found to be doing that.

Their terms are clear - if you use the coding plans they can[0] train in return. Enterprise and API, absolutely not.

The argument here is that with the Chinese labs you have zero legal recourse.

[0] opt-in, thanks

These companies have hopefully captured all of their traces and now have enough to fine-tune an open model and host themselves.

Inkling feels like the right base - not obsessed with benchmaxxing on coding but rather being adaptable to the task required

For tasks like GTM, support, content writing etc. seeing 80%+ savings

Part of the motive of moving the WEM to 5 minute intervals was to eventually leave this option open.

The largest renewable project in the world is being planned in this area[0] so it's feasible that it all may be connected one day

[0] https://wgeh.com.au/overview/

I got into a dispute with my embedded provider because of a bad meter and came to discover through friends and family in the construction industry as well as speaking to a former sales person in the industry that there is a lot of additional corruption in the process with straight up payments being made to win installs with developers.

When it came time to switch providers in our building, strata was promised electric vehicle chargers as part of signing a new deal with a new provider. They never delivered because they found an escape clause because of fire safety approval.

We're now locked in for years (again) and they've already increased rates once in the first year.

Nobody in the entire chain works in the interests of residents or owners. It's a completely broken system and a thorn in the side of otherwise advanced and progressive Australian energy policy. It needs to be abolished ASAP.

I still pay more for my single apartment living alone in electricity than what family and friends do in full large homes with air conditioning, 4-6 residents, heated pools, etc. It's astonishing.

1. Reiterate the cache issue from other comments already here. there is a lot of optimisation in harnesses around caching and a proxy model blows that up

2. Coding agents are model aware - they already route code discovery to mini / flash models, planning to heavy models, workflow design to ultra, implementation to mid / high etc. They know when they're exploring, planning, implementing, reviewing etc. and which model class to select and when it fails.

With a proxy you're breaking this control loop and feedback. It doesn't know, for ex. that it just attempted with deepseek v4 and it failed, lets try Opus?

3. How are you going to RL improvements and prevent the router becoming stale? You only have access to your own internal prompts and ~thousands of samples.

This is RL'd on one orgs codebase. There are going to be a lot of prompts you haven't seen before and have no insight to on how to route correctly, and you have no insight into users HF to improve your own model. Orgs aren't going to share their traces with you, so you need other sources to train on and improve

There are also new model releases every week that you need to keep up with - whats the story going to be here

4. Publish evals by running terminalbench / deepswe bench. Show us the performance / cost / time chart vs the other agent and model sets. If you can show gains there, you have a very simple value prop to sell where you can charge for a % of the saved costs

When I first started blogging around 25 years ago, he would have been amongst the first 10 readers. He linked to me, emailed me privately with feedback, praised posts and would call bullshit when he saw it.

He was never competitive with other blogs or bloggers and was never tied up in drama. He was very often a mediator in behind the scenes conflicts and was obsessed with truth over getting the scoop.

He loved tech and startups and most of all loved seeing other succeed and didn't have a gram of resentment within himself.

Everybody from that post-dotcom crash era of tech owes Om a large debt of gratitude. He will be missed. RIP Om.

while even a mildly bad agents.md can be _very_ bad for the agent. they rot very quickly which is why human curation is essential.

same with memory - a lot of the self-learning tools that are becoming popular now degrade agents over time - which is why you end up being able to run an eval with no context and it performs better

> but that's why agentic coding can still be considered a "skill".

yes - far too many cases of throwing a kitchen sink of prompts, skills, tools etc. thinking the llm will sort it out. you need to constantly prune, eval, tweak, observe, update etc. in a loop

https://aws.amazon.com/marketplace/seller-profile?id=bf9b432...

Comments URL: https://news.ycombinator.com/item?id=48422993

Points: 235

# Comments: 105

that was only because it was free

May even be an order of magnitude more

modern blocking is behaviour / heuristic based