NyanK ツ

1.8K posts

NyanK ツ banner
NyanK ツ

NyanK ツ

@straydeg

Prev @phnatanim • Software Engineer • Backend Developer • Blockchain and Crypto enthusiast

Ethiopia Katılım Ocak 2025
383 Takip Edilen157 Takipçiler
Sabitlenmiş Tweet
NyanK ツ
NyanK ツ@straydeg·
Back here again. I'm tired of getting suspended. What's wrong with X algorithm?
English
0
0
10
2.1K
Zun
Zun@Zun2025·
tbh the @ambire wallet dev team deserves more credit than they get, they take care of their wallet codebase in such way that even automated security scanners mark them very safe, while plenty of other popular extensions fall below 90 score not only this time, I have seen multiple times that ambire often rank top in terms of security, UI, UX everything. Ambire wallet score : 97/100 link : crxplorer.com/extension/ehgj…
Zun tweet media
English
25
9
110
3.2K
NyanK ツ
NyanK ツ@straydeg·
@trq212 lmao imagine killing the user cuz they are prompting and costing money
English
0
0
2
341
Thariq
Thariq@trq212·
every now and then I remember you can run the "please save me money" prompt and it will actually work
Thariq tweet media
English
67
32
1.1K
156.4K
Michael Truell
Michael Truell@mntruell·
For the next month, we’re doubling Cursor usage for new users you invite on the Teams plan. Enjoy!
English
305
117
1.9K
58.6M
adaption
adaption@adaption_ai·
Compute has been the great divider in AI. For the next 30 days, AutoScientist is on us. The science is in your hands, the compute is on the house. Don’t inherit intelligence. Shape it.
adaption tweet media
English
19
16
185
176.2K
NyanK ツ
NyanK ツ@straydeg·
@thdxr i will be back tomorrow to understand this
English
0
0
0
50
dax
dax@thdxr·
everyone is building things for agents who is building things for asians?
English
134
20
1.3K
85.9K
OpenCode
OpenCode@opencode·
Gemini 3.5 Flash now available in OpenCode - very fast - 1M context - priced similarly to GLM, Kimi, and DeepSeek Pro
English
106
62
2.4K
111.6K
EB
EB@cesc__·
@trq212 So, Thariq, have you ever tried htmlship?
English
1
0
0
208
Thariq
Thariq@trq212·
continuing my HTML era, I had so much fun talking with Claire at Code w/ Claude about staying in the loop with long running agents
claire vo 🖤@clairevo

Soooo @trq212 has straight up changed my life with these 5 words: "HTML is the new markdown." It's so obvious in hindsight: while .md is simple to write and agents can read it well, it's a total slog to eyeball as a human. In this special ep recorded live at Code with Claude, Thariq walks me through how he: - uses HTML artifacts as interactive specs - builds throwaway micro-UIs - maintains a living design system in HTML - prompts Claude with "whatever is needed" to give it room to actually think He also tells us what comes after the SWE + PM role 👀 As always, a huge TY to our amazing sponsors: 🔀 @celigoinc - Intelligent automation built for AI: celigo.com/howIAI 🪪 @withpersona - trusted identity verification for any use case: withpersona.com/lp/howiai Watch now on YT: youtube.com/watch?v=Qrpm7E…

English
37
33
666
111.7K
NyanK ツ
NyanK ツ@straydeg·
@theo Thought you unsubed from claude
English
0
0
0
586
Theo - t3.gg
Theo - t3.gg@theo·
It's crazy what you can do with a well written CLAUDE.md :)
Theo - t3.gg tweet media
English
14
2
832
113.6K
Theo - t3.gg
Theo - t3.gg@theo·
To prevent "programmatic use", Claude Code may now request webcam access to assure user is present when prompting
Theo - t3.gg tweet media
English
552
173
7.4K
989.5K
Teknium 🪽
Teknium 🪽@Teknium·
While i have the lucky few of you who read Peters tweets here, heres a free 20$ sub to Nous Portal for Hermes Agent, where you can access 300+ models at discounted rates and all the core hermes tools, and even free models. First 100 new users only. Time to drop the lobster BAZOZFN1 100 uses. Sign up at portal.nousresearch.com/manage-subscri…
English
19
3
159
6.8K
dax
dax@thdxr·
something is going wrong with gpt 5.5 caching doesn't look like much on this chart but this it's now using 2.5x as many input tokens as a week ago and dropping
dax tweet media
English
92
25
1.3K
121.8K
OpenCode
OpenCode@opencode·
OpenCode x DeepSeek V4 Flash - free for a limited time DeepSeek V4 Flash is currently our most popular model in Go Give it a try if you haven’t already
English
120
195
3.8K
224.4K
dax
dax@thdxr·
this is the most toxic company i've ever worked at
dax tweet media
English
82
7
1.7K
288.6K
dax
dax@thdxr·
some of you need to go outside and touch ass
English
151
105
2.9K
108.5K
NyanK ツ retweetledi
Vladimir
Vladimir@vlelyavin·
@arankomatsuzaki bro 1.7 billion tokens in a day is not engineering it's a climate event
English
4
11
667
38.5K
Pramod Reddy Pandiri
Pramod Reddy Pandiri@PramodReddy1606·
@thdxr Guilty. I spent 3 months optimizing token usage instead of just shipping the thing that worked.
English
2
0
22
2.6K
dax
dax@thdxr·
programmers are so good at rationalizing themselves out of building things that work for a lot of people it's why programmer takes on business are usually exactly backwards
English
42
11
980
59.3K
Shikhar
Shikhar@shikhr_·
@theo Do I need to watch this video if I don't use Claude Code??
English
3
0
5
2.1K
Theo - t3.gg
Theo - t3.gg@theo·
If you use Claude Code, be careful what you put in your commit messages...
English
54
29
850
87.5K
0xVox
0xVox@Synslius·
I will now swap out my Max 20x with my dearest Mimo. @_TobiasLee Thanks Lee and team for the opportunity, they’re running a 100T token giveaway, please submit your work with their link, and usually you’ll get their response in no time after they review your works. There’s a good chance you’ll get a Pro/Max plan for a month. And the Pro plan itself gets you 700M tokens.
0xVox tweet media
Xiaomi MiMo@XiaomiMiMo

Xiaomi MiMo-V2.5 is now officially open-sourced! MIT License, supporting commercial deployment, continued training, and fine-tuning - no additional authorization required. Two models, both supporting a 1M-token context window : • MiMo-V2.5-Pro: built for complex agent and coding tasks, ranking No.1 among open-source models on GDPVal-AA and ClawEval • MiMo-V2.5: a native omni-modal model with strong agent capabilities A model's value isn't measured by rankings alone — it's measured by the problems it solves. Let's build with MiMo now! 🤗 Weights: huggingface.co/collections/Xi… 📄 Blog: #blog" target="_blank" rel="nofollow noopener">mimo.xiaomi.com/index#blog

English
1
0
1
973
Sajid Ali Anjum
Sajid Ali Anjum@sajidalianjum·
@thdxr I know most will say yes, but I would suggest that the opt out should be straightforward and presented on first launch, not buried deep inside settings like VS Code does.
English
1
0
5
726
dax
dax@thdxr·
opencode go is currently zero data retention however we can increase limits and make it all more sustainable if we collect data to train future open source models you can opt out of this - is that something you'd be ok with?
English
235
15
621
85.8K