You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardexpand all lines: Monthly Notes/Jun 2024 notes.md
+4-1
Original file line number
Diff line number
Diff line change
@@ -21,18 +21,21 @@
21
21
## launches
22
22
23
23
- luma ai dream machine https://news.ycombinator.com/item?id=40670096
24
+
- arc-agi benchmark
25
+
- got 71% or 50% solution https://x.com/bshlgrs/status/1802766374961553887
24
26
25
27
## discussions and good reads
26
28
27
29
28
30
-[cost of self hosting Llama 3](https://blog.lytix.co/posts/self-hosting-llama-3)
29
31
- Assuming 100% utilization of your model Llama-3 8B-Instruct model costs about $17 dollars per 1M tokens when self hosting with EKS, vs ChatGPT with the same workload can offer $1 per 1M tokens.
30
32
- Choosing to self host the hardware can make the cost <$0.01 per 1M token that takes ~5.5 years to break even.
33
+
-[A Picture is Worth 170 Tokens: How Does GPT-4o Encode Images?](https://www.oranlooney.com/post/gpt-cnn/)
0 commit comments