News for hackers. Stuff that matters.
Re:Kimi K3 is now live by refulgentis on Thursday July 16, 2026 @02:26PM (#48938267)
Fable is by Anthropic, and this is too expensive, GLM 5.2 is roughly the same quality at a much cheaper price.

(I mantain a client with llama.cpp and 101 models across 14 companies by http)

Re:Kimi K3 is now live by LaurensBER on Thursday July 16, 2026 @02:34PM (#48938391)
As much as I like GLM 5.2 it's clearly a step below Opus (or even Fable) for more complicated tasks. I would place it at Opus 4.6/4.7 level.

Having said that, the safety system on Fable makes it an extremely unattractive model. It feels that half of the time you're paying double for Opus level performance.

Re:Kimi K3 is now live by jml78 on Thursday July 16, 2026 @03:00PM (#48938759)
Fable won’t even generate a jwt to test endpoints because it is security related. It is crazy capable but useless for real work
Re:Kimi K3 is now live by weego on Thursday July 16, 2026 @04:21PM (#48939715)
Unless your real work is outside the scope of one tiny niche of work.
Re:Kimi K3 is now live by arcanemachiner on Thursday July 16, 2026 @05:51PM (#48940757)
Eh, it doesn't hit you until it hits you.

I finally bumped into a task that Codex would refuse to work on.

Was I attempting to reverse-engineer a GPU driver? Yes. Was I trying to hack into the DoD? No.

I wasn't doing anything wrong, but that's not what OpenAI's safety mechanisms thought.

Re:Kimi K3 is now live by pimeys on Thursday July 16, 2026 @05:28PM (#48940490)
GLM has issues with tool calls and nested JSON and it wastes tokens pretty often. I see it being a bit above half the price of Opus in a bit more complex eval tasks. With some RL you could probably get the tool calls sorted and the price down.