101–110 of 740 posts
Earlier quoted context omitted.
I had Fable bail on me because I used the word autopilot on a project. Changed to something unrelated, and off we went.
I haven’t hit the Fable guardrails a single time after substantial usage. And I’m working on a ML project (a game AI). I don’t doubt people are hitting it… shrugs
2nd time was literally me being lazy and telling it to commit and open a PR.
Very strange.
What I don't see is vast areas of industry finding $10s to $100s of billions of value in LLMs. There's no lint or compiler that can check for correctly constructed contracts. So LLMs, which should be useful to law firms, incur a lot more manual checking of their work than coding agents.
Less formal document production in other industries is likely to have less structure. That might not matter in some settings but I'm having trouble thinking of an example off the top of my head.
Earlier quoted context omitted.
I do not agree. Fable is the only model I can leave unattended and give me results for part of my work which is just devops related tasking. I can hand hold opus but I would rather just ask fable to do it and give me the result that I review and works. Opus will waste tokens and still require me to help nudge it in the right directions. I think the next gen models from china will put us in a spot that the cost can pl…
I second the parent comment. 5.6 sol xhigh is not only better than fable I can also run it forever without worrying about limits. The frontend has gotten much better too with the plugins that come with codex.
Also, Sol doesn't refuse constantly and speaks like an engineer rather than a deranged academic.
Opus 5 is legitimately terrible and can't or won't follow instructions. It is of negative utility and does more harm than good to my codebase.
Fable is just way too expensive and limited compared to GPT 5.6 Sol, and the only task that requires that level of intelligence is frontier scientific research. I use GPT/Codex primarily for coding and usually keep Claude on Sonnet 5 most of the time as I use Claude primarily to debug/brainstorm/make frontends as a supplement to GPT.
"Almost Nobody Is Using Anthropic’s Fable 5" - https://analyticsindiamag.com/ai-features/almost-nobody-is-u...
I’m not sure if the underlying data is counting subscription use for Fable, which is where a lot of people are using it because token pricing is very expensive. I wouldn’t be surprised if this was counting enterprise token usage only. As rich as enterprise customers are, they’re not exactly willing to double the cost of SWE salaries on tokens. Either way, a model used to solve the top 10% of problems that people use…
Earlier quoted context omitted.
I wish Fable were as good as you make it sound. A plan created by Fable is good, but in my case, it always contain issues caught only when it's reviewed again (whether by itself, Opus, Sol etc.). That's (almost) not different from plans created by Sol, GLM 5.3 etc. The one thing where it's genuinely better is the front-end, but then again it's far from perfect, it just needs less iterations.
Fable does far better at considering the whole picture, weighing options, and making suggestions during architecture or refactoring discussions. It’s more reliable and makes less dumb errors than Opus. It still messes up, of course. But for my working style, I definitely prefer it.
That said, Opus 5 is broken. Use 4.8 or another vendor for the build agent.
im using fable almost exclusively, i just buy a new 200$ license if i run out of capacity. its so much better, easily worth it given how much work I get done. I built a code, deploy, e2e test loop with my full aws infra, fable just implements linear tasks constantly, 5 at a time, tests the whole thing end to end if people dont see why they need a model this smart, they probably arent using ai enough
I am not doing awfully complex tasks though. I imagine a lot of other people are in a similar boat, either switching from Claude to ChatGPT or even just min-maxing DeepSeek V4 Flash 0731 or similar.
Earlier quoted context omitted.
I had Fable bail on me because I used the word autopilot on a project. Changed to something unrelated, and off we went.
I haven’t hit the Fable guardrails a single time after substantial usage. And I’m working on a ML project (a game AI). I don’t doubt people are hitting it… shrugs
Nowadays Codex handles the bulk of the implementation and Fable/Opus on the planning.
Not sure if Anthropic patched it, but early on its release the web UI Fable guardrails will trip if you mention you're a biologist.
GLM series has made it very practical to self host. If the new update for Deepseek flash holds up, I think it would be silly for some companies to not self host.