Witizenship (@witizenship) profile picture
Joined October 2024
Photo by Witizenship (@witizenship)Photo by Witizenship (@witizenship)Photo by Witizenship (@witizenship)Photo by Witizenship (@witizenship)Photo by Witizenship (@witizenship)Photo by Witizenship (@witizenship)Photo by Witizenship (@witizenship)Photo by Witizenship (@witizenship)Photo by Witizenship (@witizenship)Photo by Witizenship (@witizenship)
Did you use it in anti gravity? I feel like it's held back alot by the harness
tried out gemini 4 neon today it does not beat opus 5.5. it is good, but does not understand my intent as well as opus, and is not as thorough. for example, i asked it to add a diagonal strikethrough in a box in a web app when that box was disabled, and it failed to do it properly the first time (the line did not reach both corners properly). no doubt opus would have nailed this first try and proven it with screenshots. neon is very eager though, and it's kind of fun. i still need to do more testing on it to see what it's capable of.
1
Did Jensen plan this all just so.he could get time off to play GTA 6?
11
Getting 96% Cache Hit rate using Gemini 4 Hydrogen with Deepseek Harness via the API
16
Most likely a Antigravity issue more than a Gemini issue. Will test with DeepSeek Harness to rule out.
🚨Gemini 4 Neon 严重缓存BUG ‼️‼️‼️ 请先停手你手中的 Gemini 4 Neon Gemini 4 Neon 3 倍的速度消耗你的 Antigravity 额度!! 提示词缓存出问题了:1 分钟后命中率仅 9% Opus 5.5:约 95%(1 小时) Codex 中的 GPT:约 97%(24 小时)
1
1
3
105
Exactly as I thought. Antigravity has a lot of improvement that needs to be made @antigravity
1
7
Qwen Token Plan is Fantastic for DeepSeek Flash Usage. You get a lot bang for buck.
19
⚡️NEW: The United Arab Emirates is facing a Christmas crisis as Christmas trees are stuck at sea due to Iran's blockade of the Strait of Hormuz
19
If this is true GLM5.5 it's due to them doing their own Data Collection and cleaning and not doing any distillation at all. Calling it now.
Not sure if it's true. But if Gestalt is GLM-5.5 then Zhipu has definetly cracked something internally. It is a massive jump, how big that model has to be? So many questions, hope it will get answered soon !
174
Witizenship retweeted
Finally we will be able to use the Gemini subscription elsewhere instead of being locked to Antigravity very soon :) Google is doing phenomenal work lately and I'm 100% keeping the Gemini sub.
59
30
18
963
37,753
Witizenship retweeted
We collaborated with @AMD to bring local model inference to AMD NPUs. NPUs deliver powerful compute performance while using 2–4× less power than traditional GPUs. We teamed up to enable running models with less power! Strix, Gorgon, Krackan & more. Blog: newsroom.amd.com/news/amd-un…
AMD XDNA 2 NPUs are the world's first NPUs supported by @UnslothAI Desktop. 100+ agentic apps. Now on your NPU. bit.ly/4jqlftF
76
105
19
1,089
43,271
Witizenship retweeted
I have been testing the new Gemini 4 Neon, but the usage is quite low for my Pro account. If they can fix that, i can see this being used by everyone.
17
3
218
12,106
Witizenship retweeted
Peace through strength.
7,852
12,312
2,605
88,793
6,855,865
Or let us use it with any harness
Google has one thing left to fix. Antigravity. It's weak compared to Claude Code or Codex. As someone who loves desktop apps, it's not customizable at all and doesn't even feel strong as a harness. Either merge it into the Gemini app or lock in for the next few weeks and give us a new Antigravity experience.
22
Holy shit I'm the same age as Ohne. Damn.
ohnePixel get hits with reality check during GTA playthrough: "I just want to be free, I feel lonely right now. Why the hell am I role-playing in a relationship with a kid... I am here sitting behind a controller, 28 no GF."
106
Witizenship retweeted
Gemini 4 Neon takes the 2nd place on the LMArena agent arena Index
25
44
11
1,363
107,336
Why is my Argon usage going down when I am using Hydrogen? @GeminiApp
10
Witizenship retweeted
I said it before, AMD should be training models specifically on all of their documentation and IP, and using that to optimize things.
Working with @AMD, our models identified up to 14% PPA improvement on flagship GPU IP in less than five months—building on designs AMD’s engineers had already spent years optimizing. The same approach helped improve Jalapeño, our first custom inference chip, with gains verified on real silicon. New evaluations also show our models getting better at certain chip design tasks. We’re sharing these results and how we’re working with @Synopsys to bring our model capabilities and their trusted EDA design and validation tools to more chip designers. openai.com/index/advancing-c…
7
5
81
3,654
Witizenship retweeted
BREAKING: The Pentagon fails its financial audit for the 9th straight year.
710
5,175
105
100,581
1,036,702
Witizenship retweeted
You: Want a PS5 to play GTA 6. We: Are giving 6 away. Just repost this, reply with why you want it, we'll pick the best replies to win. Paid out in upgraded money (USDC). US only.
4,959
4,860
634
6,445
465,889