Alternative: I do a lot of commits just marked "wip" as I go, then when I'm ready to consider a PR, I rebase my branch into something for public consumption. Some commits will get thoughtful messages when warranted, others will get one line, and the PR description will tie it all together with screenshots and links to the most interesting parts.
(On a good day, that is. Though even on a bad day I don't let "wip" commits into the main branch.)
I'll dare say it would be a net positive to even expand this to the undocumented.
Many of them have dependents, it's not going to be great if your dad can't afford his insulin and is thus unable to work to provide for you.
This includes a large percentage of our farm workers who are literally getting sprayed with pesticides all day. That's another issue, but when they get sick they more than deserve treatment.
And finally, the vast majority of illnesses can be treated cheaply if irregularly do your checkups. It can cost society $200 today for a doctor visit , or 30k for an ER stay in 3 years.
That said, I think this should be handled on a state by state basis. If the people of Alabama don't believe in single-payer healthcare, or they want to forbid using single pair healthcare for contraceptive or something, that shouldn't stop a progressive state from implementing it.
> No body goes to the doctor because they want to.
This isn't entirely true, there are entire industries catering to the worried well, eg expensive precautionary full-body MRIs with unclear scientific backing, whatever it is Bryan Johnson is doing and selling these days, etc.
And exactly what counts as need flexes and changes depending on circumstance and who is asking. "Do I need a doctor for this" is not a question that everyone answers the same way.
There are certain preventive care procedures that are proven to be effective based on reliable evidence. Everyone should get those, and for anyone with health insurance they're covered at zero out of pocket cost.
The majority of healthcare spending goes to chronic conditions caused primarily by lifestyle factors such as substance abuse, over eating, poor sleep, and lack of exercise. The healthcare system can't deal effectively with lifestyle problems. Those are more in the domain of public health, social work, and economic policy.
I wholeheartedly agree, but I don't think the national politics would support that at the moment. I think we have to start somewhere that isn't controversial like extending coverage to kids. I don't think anyone is going to be against covering 8 and 9 year olds... but they might against 18 or 19 year olds. It's a foot in the door persuasion tactic rather than try to get everything all at once.
> I think we have to start somewhere that isn't controversial like extending coverage to kids. I don't think anyone is going to be against covering 8 and 9 year olds...
Not sure what gives you this idea. The major political party in power in the US today campaigned in large part on cruelty and removing subsidies and social benefits from people. There are a huge number of people who would bitterly fight against providing health care to children. It's the same mentality that bitterly fights against free school lunch for children.
I’m not cruel because I think society operates best — in terms of human outcomes — if incentives and disincentives are tied to decisions in ways that maximize the likelihood and benefit of personal responsibility.
Parents need to be responsible for their children. The state should only step in if they fail in their responsibility.
How is it folks like yourself can understand these concepts across a myriad of domains, including things like wildlife and their rehabilitation, and the importance of fostering self-sufficiency, but not this?
It’s not kindness to create people dependent on the state, or to advantage businesses that do not pay a living wage by subsidizing their employees.
Hell, look at what we’ve done to the cost of education by creating government-backed loan programs that simply allow universities to charge as much as students can afford to mortgage from their future.
>I’m not cruel because I think society operates best — in terms of human outcomes — if incentives and disincentives are tied to decisions in ways that maximize the likelihood and benefit of personal responsibility.
And how did personal responsibility make housing unaffordable?
>Parents need to be responsible for their children. The state should only step in if they fail in their responsibility.
How neat and tidy.
>How is it folks like yourself can understand these concepts across a myriad of domains, including things like wildlife and their rehabilitation, and the importance of fostering self-sufficiency, but not this?
What are you talking about? Everyone who's poor and powerless should be helped. More importantly, though, they shouldn't be taken advantage of by wealthy interests. That includes animals, that includes expectant mothers who don't make enough money to survive because the "money to survive" dial was cranked up to 100 in the last five years. But please, lecture us some more about how that's HER fault.
>It’s not kindness to create people dependent on the state, or to advantage businesses that do not pay a living wage by subsidizing their employees.
It's also not kindness to raise their rent for no other reason than you can.
>Hell, look at what we’ve done to the cost of education by creating government-backed loan programs that simply allow universities to charge as much as students can afford to mortgage from their future.
And we could end it all tomorrow by saying "the US government must fund university education". You know, like they do in Europe, or like we did a few decades ago in the United States. You're pointing to a radically predatory policy decision, designed to benefit rich people, and saying: "See? Government doesn't work!" But that's "conservatism" for you: say government doesn't work and then get elected and prove it.
I don't know if you truly believe that education costs would come down if we stopped shunting students into indentured servitude (guess which loans are the only ones that can't be discharged in bankruptcy? What a curious law of the universe that must be!), but if that's the case, then I have a fabulous bridge I'd be willing to part with for a modest price.
I will never stop fighting against people who wield the power of the state to punch down and then point the finger at those same people and blame them. It's disgusting, it's abhorrent, and it must stop.
> I will never stop fighting against people who wield the power of the state to punch down and then point the finger at those same people and blame them. It's disgusting, it's abhorrent, and it must stop.
I can see that. Your ideology creates the problems you think we just need more of your ideology to solve.
You’re not some warrior for freedom or the oppressed, you’re just another person that mistakes enabling for actual care, and thinks serving the interests of the powerful is revolutionary.
So sure, let’s build a system that forces everyone into the workforce, benefits employers who pay too little, and produces worse outcomes for children.
> No body goes to the doctor because they want to.
I routinely go to specialists for things I don't need to, because I make enough money that it's better than waiting for the issue to go away on its own.
Now imagine expanding that to the entire country, when they don't have skin in the game.
I really would prefer them to start creating customized models.
I've vibe coded Godot games extensively.
Just about every model I've tried likes to invent imaginary functions.
I was really prefer for there to be a way for me to pick model trained in whatever framework I need.
Reviewing AI generated code feels like editing a long book, and every now and then you notice some words are just completely made up. You then ask the AI to fix its book, and it will just add more AI generated words.
On one hand I want this to be a reality check to everyone who's trying to lay off real software engineers to replace us with AI.
On the other hand half of the stock market is held up by overhyped AI valuations. If the tide goes out too fast, and there is a mass realization that this stuff just isn't as good as it's hyped to be, it's not going to be fun for anyone.
For one hilarious example, Gemini (2.5; I haven't tried it with 3 yet) only knows about the old Google API for Gemini, not about the new one. So if you give it code written against the new stuff, it will often do things like, "this is definitely wrong, I know this API doesn't have this method, let me fix that".
I find Gemini 3 (and Claude 4.5) also only seem to know about the 2024 era of LLMs and will often just randomly rewrite calls to GPT5 to GPT4o, or Claude 4.5 to Claude 3.5 if it happens to find them in a file, regardless of whether I told it to do anything about that or not.
How well has your vibecoding with Godot worked? I thought about it but wouldn't the LLM be unable to add files by itself due to stuff only the Godot editor knows how to do like generating uid files and so on? I would have expected that the LLM needs a MCP or some tool calling to properly interact with a Godot project. How are you doing it?
Just add godot example games nearby and it will learn functions / usecase from them. Just say in instructions BTW you have example games in "examples" directory to check
Why use an extra tool, when you can tell the LLM where the Godot source is to be found in case it wants to investigate some details? What is the benefit of using repomix?
I'm going to treat this like Kiro, and just use it until they start charging for it and then probably switch back to VS code with its built-in agent support.
Eventually they're going to do a rug pull, and instead of paying $10 a month for tons of AI code request, it's going to be two or $300 for that. The economics just aren't there to actually make a profit, hopefully before the rug pool happens local models on normal hardware will be fast enough.
With these new developments, are there any implications for getting LLMs running well on consumer AMD chips ?
For example, the following laptop which I'm thinking of picking up, has both a strong AMD CPU/IGPU and a RTX 5080. Could we see the AMD side competing with the RTX?
I know a dedicated gpu will always be faster though.
>HP OMEN MAX 16-ak0003nr 16" Gaming Laptop Computer - Shadow Black Aluminum
AMD Ryzen AI 9 HX 375 (2.0GHz) Processor; NVIDIA GeForce RTX 5080 16GB GDDR7; 32GB DDR5-5600 RAM; 1TB Solid State Drive
I run Qwen3 Coder 30b through Ollama on an RTX7900XTX. It works great, I suspect some load gets passed to the 32gb system memory and Ryzen 7 CPU.
It's not quite as fast as like Sonnet 4 from an API, but it's really not that bad.
It's really great for quick questions so I don't have to google stuff, and it's probably Sonnet4 level of competency at achieving coding tasks.
No API served model has been fast enough to remove the urge to do something else while waiting for bigger tasks, so the UX is more or less the same in that regard.
Opencode + ollama + Qwen3 Coder has been a very reasonable alternative to ClaudeCode with Sonnet4.
That is amazing for something running locally.
It is possible that if you actually need AI to be doing all your coding, that you're going to feel differently about the setup. But as a small assistant it's great.
That's great I have been eyeing a Strix Halo and was wondering how well smaller models are doing. This is great news from the perspective of running local agents.
Is the performance decent? I'm looking at using it with 30b coding models with a local agent framework like goose to see if we can do this locally as developers instead of risking leaking code to the big models.
The chip in general is fast, it builds llvm in ~12m or so. Whisper on it is at least real time but I only ran the stream binary before sending the box away to SC25. I'm expecting it to need some work to exploit the zero copy the APU permits. So it probably will be fast but isn't just yet, at least on my toolchain.
You might think that a dGPU is always faster but the limited memory capacity bites you there (unless you go to datacenter dGPUs that cost tens of thousnds). Look at eg https://www.ywian.com/blog/amd-ryzen-ai-max-plus-395-native-... or the various high end Mac results.
AMD Ryzen™ AI 9 HX PRO 370 Processor (2.00 GHz up to 5.10 GHz)
Operating System
Windows 11 Pro 64
Graphic Card
Integrated AMD Radeon™ 890M
Memory
64 GB DDR5-5600MT/s (SODIMM)(2 x 32 GB)
But I also seriously want to run LLMs. My hunch is a gaming laptop is the best way to do this on the go without spending 5000$ for a Thinkpad with a high end graphics card.
You can ask a traditional crafts person in most the world to make you a custom one with traditional patterns and it would be significantly better. Then they can feed their family for a least a week.
Apple isn't the only one who can make a giant sock!
Apple wants to charge $150 for this sock. My premium fair-trade version, woven using traditional indigenous practices from sustainably-grown biodegradable materials, blessed via an aboriginal ritual, complete with an autographed certificate of authenticity from a rural craftsperson who subsequently follows you on social media, will cost $200. Joke's on Apple.
I think the discussion is missing the real purpose of this (and which can't be achieved by other vendors) which is to normalize carrying your phone in a way that it's recording without your holding it in your hand to make it obvious that you're recording.
Honest to God, this would discourage frequent commits.
Which will lead to a lot of work not being committed.
Thoughtful messages are for PRs.
reply