361–370 of 1001 posts
Impressions from testing Fable 5 prior to launch: • My most noticeable immediate jump was in how its frontend design was much more intentionally crafted, and delightful without feeling like 'AI vibe coded'; with better end-user usability too. • In some internal agentic harnesses, it achieved better results with about half the tokens, making it cost the ~same as Opus 4.8 price-wise! The real price increase is less tha…
Can I ask how you gained preview access to Fable 5?
"It's too dangerous it's a Mythos!!" directly contradicts the "I'm the cool AI you can totally trust" vibe it is trained to project.
Impressions from testing Fable 5 prior to launch: • My most noticeable immediate jump was in how its frontend design was much more intentionally crafted, and delightful without feeling like 'AI vibe coded'; with better end-user usability too. • In some internal agentic harnesses, it achieved better results with about half the tokens, making it cost the ~same as Opus 4.8 price-wise! The real price increase is less tha…
Can I ask how you gained preview access to Fable 5?
My experiences so far have not been positive. The cyber security nerf is ridiculous. I am working on an AI based decompiler, every single interaction with Fable on my project has been flagged for cyber security. Do they expect us to use this as a toy? Releasing a new more powerful model but not allowing normal use cases because the word "secure" showed up is a Dilbert comic, not a viable product.
Obviously there are plenty of innocuous applications too, but it's not like the people building decompilers for nefarious reasons will be explicit about it. The LLM abstraction just inherently doesn't have enough context to distinguish your intentions or your broader use cases. This is why both Anthropic and OpenAI have had to create side channel mechanisms for security researchers to establish a trusted use context. It sounds like this makes this not a viable product for you, unfortunately, and it makes sense that that's frustrating. But I also don't see what different behavior one could reasonably expect given the constraints.
If it's any consolation, these restrictions only make sense for models that are ahead of the open-weights frontier, so open-source hackers will presumably get Mythos-level capabilities in the relatively near future anyway.
/* What will happen first? * Anthropic runs out of genre names. * Anthropic changes the model naming convention. * AGI is achieved and handles its own naming. */
Anthropic has again changed the set of benchmarks they use[0]. This time they have also moved all benchmark scores to the PDF. At a glance it looks like it gains about ~5-10% over other models. the speed is about the same as opus >=4.5, sonnet 4.5, and double the speed of opus Mythos 5 Fable 5 MythosPrev Opus 4.8 GPT-5.5 Gemini 3.1 Pro SWE-bench Pro 80.3 80 77.8 69.2 58.6 54.2 SWE-bench Ver 95.5 95 93.9 88.6 - 80.6 T…
> In light of the ability of recent models to accelerate their own development, we’ve implemented new interventions that limit Claude’s effectiveness for requests targeting frontier LLM development (for example, on building pretraining pipelines, distributed training infrastructure, or ML accelerator design). Using Claude to develop competing models already violates our Terms of Service, but enforcing this restrictio…
Looks like Anthropic's definition of safety includes their own safety from competition.
The safety gates on this are extreme , and seem considerably wider than "cybersecurity and biology"; they seem to make it essentially unusable for scientists in a number of fields. I have, so far, been bumped back to Opus on 100% of my prompts. It appears it can be tripped by things as simple as a mention of equilibrium, or anything involving something that looks like chemical kinetics, even at an abstract level. Eve…
>"We’ve therefore launched the model with safeguards that mean queries on some topics will instead receive a response from our next-most-capable model, Claude Opus 4.8"
That's a very surprising solution. Imagine being asked to do something you feel you shouldn't do, and rather than refusing, you say, "Yeah I could do that but given that I don't want you to succeed at this task, I'm going to hand this one off to my slightly less capable colleague, on the assumption that they won't actually succeed. Of course you'll still be charged for all the tokens used."
It's a very interesting choice. I think I understand the business logic correctly, but it's still surprising.