301–310 of 351 posts
The title asserts there is minimal downside to switching to open models, but the article provides zero evidence that this is true, and the author hasn't even attempted it yet. The end of the article states "I’m hoping it’s going to be minimal".
I wonder if I can get a post to the front page with the title: "There are no real barriers to humans colonizing Mars next month". And at the end, "I'm hoping there are no real challenges."
This can't be for real. The title asserts there is minimal downside to switching to open models, but the article provides zero evidence that this is true, and the author hasn't even attempted it yet. The end of the article states "I’m hoping it’s going to be minimal". I wonder if I can get a post to the front page with the title: "There are no real barriers to humans colonizing Mars next month". And at the end, "I'm…
> There remains a clear penalty for being an open LLM user. Every leaderboard consistently gets topped by proprietary models served over API. Today on June 21, 2026, Claude and GPT are at the top of the Artificial Analysis intelligence leaderboard. That’s from the performance side. The compatibility side is worse too. Claude code just works, and more generally, the big two provide nice APIs that make them easy to use, and, even if it’s a low bar, are “trustworthy” in the sense that we’ve largely all agreed we don’t mind sending them our LLM queries and trust them to handle them appropriately.
> Open models are served via various means, some by the companies that released them and some by third parties like OpenRouter. Unfortunately, both of these routes are dodgier in terms of privacy and data sharing, and I would not feel the same comfort sending API calls containing client or confidential data to them3.
> The other option or course is to run them yourself. This solves the privacy issue but is at least two of expensive, complicated, and comparatively slow.
So...there's actually quite a bit of downside, then? Why the misleading title?
there is zero downside to not switching though: just use claude while it's good and subsidized, switch if rugpulled
The downside, apart from privacy concerns, is sending your money to parties you don’t want to support.
> sending your money
akchyually if you do it right, you are sending negative money; fair enough otherwise
There are several benefits:
- we cut AI spending by thousands
- there is one AI server and starting different sessions for each user, one memory/skills/etc and everybody is involved into reviewing what went wrong and why. Harness finally makes sense and pays off more.
- we can trust that the models are those that we run and not black boxes
- no more money flowing to US narcissistic entrepeneurs and no more business being tied to US legislation
Not gonna lie, GPT 5.5 Pro and Fable 5 were a tiny bit ahead, especially on longer vibecode-style tasks, but it's just not worth it.
Earlier quoted context omitted.
Heh, if you're using LLMs heavily for work I think odds are pretty good you're doing pretty trivial stuff. It might not be trivial to you, but you're probably just not very good at this.
Pretty sure the big quant shops heavily use LLM; maybe it’s trivial stuff and they just work 100 hrs/week?
Edit: To clarify what I mean by this:
Anyone who uses LLMs for larger-than-small-module code generation, pretend-not-vibecoding (a.k.a spec-driven development), or outright vibecoding, etc., is using an LLM "heavily", IMO.
The appropriate things to use them for is information retrieval, plus as a basic extra signal in debugging, code understanding, quality checks, and so on.
Also, it's not illegal to be incompetent. Most people were incompetent long before LLMs showed up, it's not some rarity.
> Open models are served via various means, some by the companies that released them and some by third parties like OpenRouter. Unfortunately, both of these routes are dodgier in terms of privacy and data sharing, and I would not feel the same comfort sending API calls containing client or confidential data to them. That's why I'm using eurouter.ai with the following routing rule for all my requests: { "model": "glm-…
The part that gets me about anthropic red lines is "of Americans", okay so the rest of the civilized world is up for grabs then? It's okay to destabalize allies with sabotaged tests (in machine learning) and data exfiltration outside America? What gets me the most is that they claim that the model should follow the https://www.anthropic.com/constitution and they claim that it's embedded into the model. However, syste…
And this is coming from a CEO who constantly claims moral superiority and advances the idea that China is bad
Earlier quoted context omitted.
What if the new model is exactly as good as the last model on launch day but better than the last model was on the new model's launch day because it was degraded? Every single time?
Makes me think of [shepherd tones](Shepard tone - Wikipedia https://share.google/xooRbF7wIIhcsTt2J ) which sounds like they're rising in pitch indefinitely
Earlier quoted context omitted.
The amount the HN community, at least from what I’ve seen, is sleeping on OpenCode Go (and zen) is kind of amazing. $10 a month gets you generous usage with the best open weight models and they claim to have zero retention and not to train on your usage. It’s unclear to me what the advantages of openrouter are but it seems to be a default I see many people talking about here.
> It’s unclear to me what the advantages of openrouter are but it seems to be a default I see many people talking about here. The advantage of OpenRouter compared to using API providers directly is that you can switch between API providers without binding your money to a single provider. The advantage of OpenRouter compared to OpenCode Go is that the price for DeepSeek-V4-Pro and MiMo-V2.5-Pro is better on OpenRouter…
“The advantage of OpenRouter compared to using API providers directly is that you can switch between API providers without binding your money to a single provider.”
Opencode Go gives you a choice between “the best” open weight models and you’re not tied down to just GLM or MiniMax and Zen gives you an even longer list of providers including Claude and GPT?
Is it that Openrouter gives you access to like… every model and provider?
Earlier quoted context omitted.
Why pay a monthly fee when you can pay for exactly the # of tokens you actually consume? The API rates are very affordable once you start to optimize for the fact that prepaid tokens seem to massively outperform other kinds of tokens. I can often do with 1 million tokens what my peers have failed to do with 100 million. For me to spend more than $200/m in prepaid API tokens I'd have to pull a 007 work schedule.
> Why pay a monthly fee when you can pay for exactly the # of tokens you actually consume? Because my 500m tokens so far this month would cost me about $500. My subscription is 100$/month.
This can't be for real. The title asserts there is minimal downside to switching to open models, but the article provides zero evidence that this is true, and the author hasn't even attempted it yet. The end of the article states "I’m hoping it’s going to be minimal". I wonder if I can get a post to the front page with the title: "There are no real barriers to humans colonizing Mars next month". And at the end, "I'm…