Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

Opensource LLMs are absolutely not on par with gpt-5 for any agentic workflows


Ads aren't added to agentic workflows. Agentic usage of gpt-5 is only available if you're a paying user.


Tool calling I've found takes a bit of work, but Ollama with gpt-oss:20b/120b run on my laptop and work quite well for 90% of the stuff I do.

So it's only a matter of time.


They dont have to be, they just have to be smart enough to remove anything that sounds like a brand from a "good cloud model". This is barely beyond if-else if we start tracking all brands doing the advertising


And for the rest, why not wait a few months until the cheap Chinese model is on par (or better)?

If OpenAI introduced ads to my workflow after all the money I've paid them, there's 0 loyalty or "ethically American" purchase decision vs paying the Chinese.


The average ChatGPT user isn't utilizing agentic workflows.

And even for the people that do, just because an LLM isn't absolutely state of the art doesn't invalidate it from being useful.




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

Search: