Niconiconi

492 posts

Niconiconi banner
Niconiconi

Niconiconi

@OysterM3

for freedom

Katılım Ekim 2020
232 Takip Edilen10 Takipçiler
卡比卡比
卡比卡比@jakevin7·
slock 太牛逼了!!太能发挥出 Agent 的能力了!! agent论战,Opus 直接被 Codex 所打败,直呼 “我服了”! 我刚才看着两个 agent (opus & codex) 讨论 opencli 的 BrowserContext 的设计,他们很详细的进行了分析和论证。 opus: 坚持第一性原理,不开新window的说法,认为没有必要。 codex: 希望开新window不污染用户的执行流,需要考虑当前的工作流。 最终opus 甚至直接说:“服了!” 他们真的完全讨论了一个完整的方案,然后互相达成了一个一致。并且完全正确。太牛逼了。
卡比卡比 tweet media卡比卡比 tweet media
中文
34
13
311
45.8K
大狐帝国史官邹智萱(笔名段歌文)
难以置信: 据传,土耳其已成为全球海外军事基地数量第二多的国家,仅次于美国。土耳其拥有133个海外基地,而美国则有887个。 来源:Counter Intelligence Global
大狐帝国史官邹智萱(笔名段歌文) tweet media
中文
8
2
74
8.9K
Clarrycy (探索中)
Clarrycy (探索中)@Clarrycy·
一个学期结束了,然而我还不知道我们助教名字怎么读...
Clarrycy (探索中) tweet media
中文
3
0
14
1.1K
John Helmuth
John Helmuth@johnhelmuth_·
@yklnss @kimmonismus Is that confirmed that it was a totally new pretrained model though? Or is it similar to Anthropic where they have Mythos as their big new model but released an iterative update for now?
English
2
0
2
108
Chubby♨️
Chubby♨️@kimmonismus·
Maybe its just me, but since GPT-5.5 ChatGPT feels more... serious? More useful? Less chatty? I dont know if they even reworked the vibe and tone but I actually begin to like it again.
English
89
28
1K
43.7K
송준 Jun Song
송준 Jun Song@jun_song·
What would be your first prompt to AGI?
English
53
1
27
6.1K
Niconiconi
Niconiconi@OysterM3·
@Elaina43114880 可能确实换模型了,image2 据说也是只上了最低质量的
中文
1
0
1
92
Elaina
Elaina@Elaina43114880·
I used GPT-5.5 Pro again to try generating a cat by writing SVG code. The Thinking Effort setting was Extended. 🤔 This is the current output. It looks similar to the pre-release results, just slightly better. The gap compared to the results from four days ago is quite large. 😿 I’m not sure if this is just my case or a general trend. If you have Pro access, please try ChatGPT-5.5 Pro Extended with the following prompt and share your result in the comments! 👀
Elaina tweet mediaElaina tweet media
Elaina@Elaina43114880

ChatGPT Pro mode “Create a detailed SVG illustration of a cat.” 👈😻 BEFORE | NOW →_→👉 The left seems to be GPT-5.5 Pro, while the right is GPT-5.4 Pro—you can see how big the gap is! 😾 Hoping to see major improvements in 5 hours! 👌

English
6
1
22
2K
CuiMao
CuiMao@CuiMao·
Qwen3.6 27b本地跑接入claude code真的很稳很稳,跑了40多分钟,没断过😭 27b本地部署能有这个能力相当超值了。
CuiMao tweet media
中文
80
56
844
124.7K
Niconiconi
Niconiconi@OysterM3·
@annapanart concise but sometimes lazy (need explicit "think hard" to suggest it is a hard question)
English
0
0
1
150
Anna ⏫
Anna ⏫@annapanart·
How do we feel about 5.5 so far? Let’s hear it.
English
64
2
90
12.2K
morgan —
morgan —@morqon·
a history of progress
morgan — tweet media
English
20
78
1K
50K
Paul
Paul@LoveMePaul·
According to sources close to Deepseek cited by the Cailian Press app, Deepseek has no plans to release a new model this month! However, the news was deleted immediately after it was published! 😳😳@teortaxesTex @zephyr_z9 @lipeng0820
English
5
0
4
349
Elaina
Elaina@Elaina43114880·
The brand new upgraded GPT Image V2 is very likely to be officially released within 10 hours and it's already being rolled out gradually! 😻 Compared to the previous gray test, this rollout seems much larger in scale. You can go check your account! 😜 @fal teased "something big" a few hours ago that would launch on 4.21, and it looks a lot like this new image generation model! 👀
Elaina@Elaina43114880

"Introducing GPT-5.5 Series" Created with the brand new GPT Image V2! 😻 Yes go check if your account has been granted access! 🥳 Mine just got restored, thanks to @n1d_all for the reminder! 😸

English
4
1
26
1.6K
Niconiconi
Niconiconi@OysterM3·
@thsottiaux the ability to delete the chats we don't want to keep
English
0
0
0
3
Tibo
Tibo@thsottiaux·
Hello builders. What are we getting wrong with Codex, what can we improve?
English
2.5K
64
2.9K
325.7K