I don't understand how people are angered by this. I understand that it may be difficult to plan, but in the end, we're getting more without being charged. No-one's forcing folks to use up credits. Take it for the bonus it is.
Fable extended until 19 July
51–55 of 55 posts
Re: Fable extended until 19 July
#52I don't understand how people are angered by this. I understand that it may be difficult to plan, but in the end, we're getting more without being charged. No-one's forcing folks to use up credits. Take it for the bonus it is.
[dead]
Re: Fable extended until 19 July
#53This indecisiveness is ridiculous, and I am planning on switching back to GPT in the near future from Opus 4.8.
Re: Fable extended until 19 July
#54Not to mention how many different ways their communication can be interpreted just because of bad English.
Re: Fable extended until 19 July
#55Question to HN: How many of you actually need the SOTA level intelligence of Sol and Fable? What kind of tasks do you use it for, and what did you do 6 months ago when SOTA models were as intelligent as today's B team? The other day I tried a 31B model from a Canadian company and felt this is good enough for 80-90% of my tasks. (For the cuorious: North Mini Code. Free on OpenCode/Zen right now. No affiliation :) )
Fable is the first one I found could bring brainstorming concepts closer to what I was striving for instead of adding in clutter and defocusing.
... and then it stopped having that ability to build on create concise, accurate summaries and expand on them. Same problem with GPT 5.6 Sol. I even tried and old prompt in the (more nerfed) recent version. The core initial thinking ability lowered, and I'm getting the same over-metacognition and epistemology as it tries to pull at threads in the brainstoriming process again.