| ▲ | felixgallo 7 hours ago |
| Absolutely zero people, rounding up generously, are replacing Fable with local or Chinese models. |
|
| ▲ | colingauvin 7 hours ago | parent | next [-] |
| I am because Claude has figured out I am a biochemist and therefore even asking Fable what the weather is gets me bumped back to Opus, sometimes even Opus 4.8 instead of 5. Kimi? GLM 5.3? DeepSeek? No such problem. I can literally open a new chat with just "Hello" and it gets bumped. |
| |
| ▲ | not_a9 3 hours ago | parent | next [-] | | Memories break Fable 5 for me as well in chatbot. I ask Opus a lot of sec related stuff and now if I even type “hello” in chat it gets insta-downgraded to Opus 5. | |
| ▲ | MagicMoonlight 7 hours ago | parent | prev | next [-] | | [dead] | |
| ▲ | felixgallo 7 hours ago | parent | prev [-] | | [flagged] | | |
| ▲ | dgellow 7 hours ago | parent [-] | | Fable guardrails are insanely restrictive, are you denying that’s the case? | | |
| ▲ | felixgallo 7 hours ago | parent [-] | | [flagged] | | |
| ▲ | kami23 6 hours ago | parent | next [-] | | Yes that is exactly what's happening. Claude keeps track of memory if you've turned that on so all conversations are somehow tracked over time Claude randomly will mention that I'm a developer while I'm asking unrelated questions and say oh because you're a developer you might like this or because of my background and infrastructure you might find this interesting and I always get creeped out by it. They have the concept of incognito chats, but I can see those being worse without context from other conversations happening. | | |
| ▲ | felixgallo 6 hours ago | parent [-] | | it's not 'somehow'. In Claude Code, type /memory to be able to edit the memory files if you've turned that feature on. If you're a biochemical weapons researcher who has somehow managed to both turn the feature on and fill up the memory with attempted biological weapons research, you can (a) turn that off or (b) go and edit the files to remove objectionable lines of attack. Regardless, the number of innocent biochemists who have been hamstrung by Fable is essentially zero (but somehow they have all shown up on Hacker News to decry Fable), and the number of non-innocent would-be-biochemists who would love to have unrestricted Fable help them with their non-innocent biochemical research is absolutely greater than zero. | | |
| |
| ▲ | colingauvin 6 hours ago | parent | prev | next [-] | | It has figured it out through the software that I work on, data that I analyze, questions I ask, etc. I guess I can't prove it's because I'm a biochemist, but that's the only thing that makes any sense. Either way it won't let me use Fable. | |
| ▲ | dgellow 6 hours ago | parent | prev [-] | | Im starting to doubt you actually used fable |
|
|
|
|
|
| ▲ | cmenge 7 hours ago | parent | prev | next [-] |
| Just cancelled my Claude subscription and used Ox Alpha Free through OpenCode (so that's one). In my view, from the testing I did since Thursday, it's better than Fable. I had just finished a rather large task that Fable completed, including a /review and an /ultrareview. Ox Alpha found bugs that Fable and Opus missed, and it continued to build things like a pro. It does have issues with availability - but it's on a free promo right now. That also means that I don't know how much it would have cost if I had to pay API prices for it, which might not be cheaper than the subsidized small company / consumer usage, but for large companies paying API prices for either offering, the difference will be considerable. |
| |
|
| ▲ | tyleo 7 hours ago | parent | prev [-] |
| I almost feel like there's some sort of paid campaign going on in Hacker News promoting the Chinese/open models. I feel like every day I'm hearing about how the frontier labs are dead but your experience is the same as mine. My company pays for Claude AND Codex but we never really use the open models for anything critical. |
| |
| ▲ | dgellow 7 hours ago | parent | next [-] | | Doesn’t matter if your company pays for Claude, Anthropic and OpenAI valuations and expenditures commitment requires them to win the vast majority of the market to make economical sense. And the Chinese competition makes that very unlikely, to say the least. They likely won’t disappear fully but their “free” lunch as the AI darlings is done, on paper. Will be interesting to see how they adapt | |
| ▲ | ddxv 2 hours ago | parent | prev | next [-] | | Sure, I'm being "paid" by the fact that it costs pennies a day to use Deepseek and if I could afford the hardware then I could run it locally. Meanwhile, Anthropic is obviously a threat to open weight models and actively lobbies the US Government to have them banned or controlled. So yeah, I and I guess others, are quite active in whatever little way we have available, to up vote new models and share stories. | |
| ▲ | tokai 2 hours ago | parent | prev | next [-] | | [dead] | |
| ▲ | felixgallo 7 hours ago | parent | prev [-] | | It's absolutely a campaign. Every time anyone says anything about Claude, immediately and inorganically there's a bunch of people claiming to be biochemists who are constantly shut down by their work, people saying that they run out of tokens instantly even on Premium, people saying they get even better results on their GTX 4050, and people saying that Grok is better, or OpenAI is better. It's probably several different campaigns each run by different tranches of the competition. Reminds me of the good old days in which every criticism of bitcoin was immediately jumped on by nine or ten pretend Venezuelans who asserted that it was the only thing permitting their family to evade government currency controls. | | |
| ▲ | codexon 27 minutes ago | parent | next [-] | | I'm not a biochemist and I have been blocked by fable and opus for "cyber" just for doing things like asking it to ssh into one of my servers, look at a CVE, or do work in assembly. Been rejected to their cyber verification program 3 times already. | |
| ▲ | hgoel 6 hours ago | parent | prev [-] | | "Everyone that disagrees with me is astroturfing" is not going to lead you to being in touch with reality. | | |
|
|
