I'm so excited for another model I will never effectively use because I'm not overpaid to live in San Mansisco.
Claude Fable 5.1 and Claude Mythos 5.1
951–960 of 1001 posts
Re: Claude Fable 5.1 and Claude Mythos 5.1
#952To be honest, these frontier model releases have become boring for me. Opus 4.8 was already good enough for most of my use cases. I don't have any projects right now that I would use Fable for instead of Opus. So when I see announcements like this I just think "that's cool I guess" and then go back to using weaker/cheaper models. What's far more exciting right now is models like DeepSeek V4 Flash and GLM 5.3 Flash. T…
When hn first started taking llms seriously maybe, 2-3-4 years ago (?) one of the most interesting recurring comments was that the real research goals in the field would be reducing cost, doing more with fewer parameters, making lean models, and generally improving efficiency. Of course, those research goals run counter to the need to raise capital and do massive real estate land grabs for data centers, so they are not being prioritized by the top firms running the bubble game.
Re: Claude Fable 5.1 and Claude Mythos 5.1
#953I am finding that I am now less interested in better models than I am in token budgets. My issue with Anthropic models now is that I don't feel like I can rely on them as a daily driver because they'll dry up before my quota resets. I am becoming dependent on AI to make a living, and I need predictable spend on it. If I know I can't use a model regularly all month, my enthusiasm is limited. I urge Anthropic to get be…
GLM 5.3-flash fits the bill
and $0.15 1M input, $0.50 1M output
I am a huge enthusiast of running local models, but when multiple quality USA vendors provide models like GLM 5.3-flash, I run locally just for the fun of it.
For the purposes of comparing to Fable 5.1, I would mention GLM 5.3 that is about 1/12 the cost.
Re: Claude Fable 5.1 and Claude Mythos 5.1
#954I am finding that I am now less interested in better models than I am in token budgets. My issue with Anthropic models now is that I don't feel like I can rely on them as a daily driver because they'll dry up before my quota resets. I am becoming dependent on AI to make a living, and I need predictable spend on it. If I know I can't use a model regularly all month, my enthusiasm is limited. I urge Anthropic to get be…
I am on the Claude Max 20x plan, and this still happens when using Fable 5/Opus 5. I would run out of weekly quota in 2 days, whereas Opus 4.8 would last the entire week, and sit at about 80-90% at the end.
Same here. Over the last two weeks I switched back to Opus 4.8 and turns out that still seems to last the week like it used to. These new models must be eating tokens.
Re: Claude Fable 5.1 and Claude Mythos 5.1
#955> For example, in testing by the investment firm Millennium, Fable 5.1 found the cause of a rare crash on their internal systems that none of their engineers (or any other model) had been able to explain after several years of trying. Say what you will about LLM-generated code, but stories like this give me hope that software will never be as buggy as it once was.
I use Kimi K3 and GLM 5.3 to find old bugs and improve old code, and would try Fable 5.1 if I could afford $50 for 1M output tokens (I am retired and all my research is self funded now)
I like to start by prompting with “examine this code base for problems and improvements and write to IMPROVEMENTS.MD” and then carefully look over the suggestions, and either fix myself or let the model+coding harness try.
Re: Claude Fable 5.1 and Claude Mythos 5.1
#956I am finding that I am now less interested in better models than I am in token budgets. My issue with Anthropic models now is that I don't feel like I can rely on them as a daily driver because they'll dry up before my quota resets. I am becoming dependent on AI to make a living, and I need predictable spend on it. If I know I can't use a model regularly all month, my enthusiasm is limited. I urge Anthropic to get be…
I moved off my $200 max plan with Anthropic because of this. OpenAI gets it though.
Re: Claude Fable 5.1 and Claude Mythos 5.1
#957Earlier quoted context omitted.
Christ. With such waffly garbage in its system prompt no wonder its output is shit.
The system prompt is probably produced by a model as well, I would be very surprised if anyone at Anthropic ever opened it with an actual text editor
Yes they should just use Sol to write their prompts.
Re: Claude Fable 5.1 and Claude Mythos 5.1
#958Earlier quoted context omitted.
I'm a heavy user and fable is great the #1 reason I stopped using it was the horrible safegaurd filter. I found sol close enough in capability and have only been blocked when my request was an obvious offensive cyber work. Fable blocked me on almost everything. Optimizing a OS build? -> block Securing a container -> block 60% is nowhere near enough for that safegaurd system. This just means I am going to be blocked h…
I only use OpenAI models, and Sol is the only one to refuse me yet, and ofc it was completely bogus and I was unable to convince I was just working a regular bug for a well-known product for a well-known company using my official github account. Aaargh.
You generally don't even have to convince it, or at least I don't. I just paste the error into the prompt window, and say "you got blocked, try again", and it'll just say, "Oh, that's because ...", then do it.
Re: Claude Fable 5.1 and Claude Mythos 5.1
#959Earlier quoted context omitted.
I'm a heavy user and fable is great the #1 reason I stopped using it was the horrible safegaurd filter. I found sol close enough in capability and have only been blocked when my request was an obvious offensive cyber work. Fable blocked me on almost everything. Optimizing a OS build? -> block Securing a container -> block 60% is nowhere near enough for that safegaurd system. This just means I am going to be blocked h…
I never hit Anthropic's safety filter when I'm doing something illegal, only when I'm not.
This makes me wonder how often you are doing illegal things!
Re: Claude Fable 5.1 and Claude Mythos 5.1
#960Earlier quoted context omitted.
Please bring to the other models, and also please only apply the AI text watermarking only to EU citizens. I may not be able to tell when Claude writes about things i don't know, but in CC it writes about my code and it is obvious.
My reading of the law was that watermarking is not required by it at all. It’s a convenient excuse for the companies that want to add watermarking.
My read was that watermarking is not explicit requirement, but that it could be in something like metadata that goes with it (if generated a word doc, for example). But writing comments in your codebase, the EU will want a digital trail there.