|
iad1::1768152142-sheNPiKDya9eb2ldMmv3Mli823fSL7F7
Why your LLM bill is exploding — and how semantic caching can cut it by 73%
Related Posts
Stopping bad guys from using my open source project (feedback wanted)
Frustratingly, this was a semi-private draft that got posted to Hacker News before I could make edits. I’m leaving the post up as is because […]
AMD CEO: Pricier Ryzens will probably get more powerful NPUs
Image: Mark Hachman / IDG You’d expect that more expensive PC processors would feature faster clock speeds, more cache, more powerful integrated graphics. Future Ryzens […]
Using reinforcement learning and $4.80 of GPU time to find the best HN post
Background: I’m Kyle, the founder of OpenPipe. OpenPipe is a managed fine-tuning service that makes it easy to build your own LLMs that achieve very […]