Hacker Newsnew | past | comments | ask | show | jobs | submit | throwaway2027's commentslogin

I'm starting to explore alternative options because Claude has become an awful value proposition. Any suggestions?

I turned off Anthropic properly and switched all of that over to OpenAI yesterday. (I use other models for other things too, especially DeepSeek in Pi).

Honestly aside from the voice it uses you wouldn't notice a difference. Switching costs are low, vote with your wallet.


> I turned off Anthropic properly and switched all of that over to OpenAI yesterday.

Same, just a while longer ago.

I much prefer how OpenAI models write to Anthropic's, will probably revisit Anthropic in a generation or two. Context size is more limited, but no critical forgetfulness due to compaction so far, though I also like having plan files around both for future reference and improving chances of success at long form work.

Also tried out Kimi K3, was nice but slow (and apparently routed some requests to Claude anyways), GLM 5.3 was faster and still pretty good but the token allowances were kinda limited.


OpenAI is a better value proposition too because they give you effectively infinite image generation + chat usage, which is separate from work/codex.

So you voted for Kodos instead of Kang [1]. Local models are the way out of the rug pulling

[1] https://m.youtube.com/watch?v=BUAnyVAanac&ra=m


I don't actually disagree, and advocate that for now the thing to do is use both.

You need to use frontier models to understand where the puck is going, but also to use local ones for anything remotely sensitive.


I would like to have alternative to chat - model and provider agnostic (BYOK), but with history, project, maybe memory, with good search and quality tools. I know openwebui and i dont want to host it.

codex (their app) is pretty good and lots of banked resets, luna is cost effective and Astra seems better than Fable for many tasks. Most important one is less refusals and I can use it the way I want without the fear of getting banned. I do like Claude Code a lot when it comes to pure coding use cases but the work often touches outside code and I don't want to keep switching

> I do like Claude Code a lot when it comes to pure coding use cases

The harness is great, but opus is such an arrogant little prick that spews out unintelligible word salad. Opus 5 is so bad at communication it amazes me that somebody green-lit it. It's absolutely awful.

The fact that this isn't an acknowledged regression (and Fable 5.1 isn't much better) leads me to believe that people at Anthropic actually like Opus 5's output.


Of the major providers, Codex/Astra. By far the highest quality model, especially for cross-discipline work.

Opencode Go.

This is why I'm hesitant to buy Google AI again. I don't want to risk some npm install compromising my Google account which also happens to do AI coding.


I think this is a move to get people off the subscription and move to API. The weekly usage is still awful altough it seems they're trying to fix it but I'm not hopeful.


Why would anyone do that given how subsidized subscription usage is?

If anything they'd keep the sub and use the API if they blow past the usage.


Why do you think they want less people subscribing?


> Why do you think they want less people subscribing?

Losing money on each subscriber?


very easy to lose money on subscription, very easy to make money on api pricing


why though? I doubt subscribers are moving the need for ARR, even for OpenAI


I wonder if these benchmarks swap words, meaning and more because you might as well be benchmaxxing for specific words. I notice a lot of recurring just structural sentences coming back in smaller LLM models where they're fit for a specific task which is fine because most of the work we do is repetitive and there are patterns to learn but they should be word agnostic which I wonder if LLM can really fix.



That series was prescient.


"An update to our downloads policy and Terms of Service"

https://suno.com/blog/suno-updates-tos

https://suno.com/terms-september-2026

tl;dr They will watermark songs you generate and remove older models and restrict paying customers to max 20/60 song downloads a month.



"The model makes an honest mistake and mistakenly deletes $HOME instead."



I had this in mind when I first saw this project too LOL

Every year I need to rewatch this talk


That's quite slow I'm getting 8-12 t/s on a 13 year old CPU. (Speed varies by context size and other settings who knows)

https://news.ycombinator.com/item?id=48354801


Yeah, I'm seeing 8-9 t/s on a Xeon CPU E3-1270 V2 @ 3.50GHz with an old Nvidia Quadro K2200 (4GB). I run gemma4:e2b and gemma4:12b-it-qat on Ollama.


But OP is using Q8 and you're using Q4?


Thank you for sharing / linking!


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: