Dziky💪🏿

6.3K posts

Dziky💪🏿 banner
Dziky💪🏿

Dziky💪🏿

@dzikyDonnyMaps

AI Software Dev | Building Tools & Systems | Career & Tech Tips

Midrand, South Africa Katılım Ocak 2019
6K Takip Edilen10.1K Takipçiler
Sabitlenmiş Tweet
Dziky💪🏿
Dziky💪🏿@dzikyDonnyMaps·
✅ Works perfectly in Cursor too! Full steps: 1. Install uv 2. uv tool install –force git+github.com/Alishahryar1/f… 3. Run: fcc-server (keep terminal open) 4. Get free NVIDIA key → build.nvidia.com/settings/api-k… Paste in: http://127.0.0.1:8082/admin 5. In Cursor → settings.json add: “claudeCode.environmentVariables”: [ { “name”: “ANTHROPIC_BASE_URL”, “value”: “http://localhost:8082” }, { “name”: “ANTHROPIC_AUTH_TOKEN”, “value”: “freecc” } ] Restart Cursor. Done! Free Claude Code agent. Repo: github.com/Alishahryar1/f…
English
2
8
74
10.7K
Anish
Anish@shwarmadev·
@dzikyDonnyMaps I think you're right. We think our product is good to get eye-balls and to get rev in your door without having to spend too much on marketing. Our product is not even 20% complete yet, we have big ambitions in this space :)
English
0
0
2
39
Anish
Anish@shwarmadev·
Today, we introduce Claude for Marketing. In one chat, Fastlane deploys social media accounts, generates viral content, and posts everything automatically. You built a product, now make sure the world sees it.
English
193
242
3.5K
1.8M
Dziky💪🏿
Dziky💪🏿@dzikyDonnyMaps·
@eng_khairallah1 Same Claude. Completely different results. Boris dropping straight alpha as usual. Bookmarked the breakdown this is the kind of stuff that actually moves the needle.
English
0
0
0
12
Khairallah AL-Awady
Khairallah AL-Awady@eng_khairallah1·
Boris Cherny, the creator of Claude Code at Anthropic, just explained why some users save 10 hours a week and most save zero in this podcast he breaks down exactly how most people are using 10% of Claude: - the 10% you lose to CLAUDE.md before typing a word - the workflows that chain tasks so you stop copy-pasting between steps - the batch operations that handle 30 files in the time you do 1 - the automations hiding behind settings most users have never opened if you've been using Claude for months and still do everything one prompt at a time, you're losing hours every week. probably 10+ instead of another show tonight, watch this make sure to bookmark it before it gets lost in your feed my breakdown of all 30 workflows is below
Khairallah AL-Awady@eng_khairallah1

x.com/i/article/2057…

English
43
61
408
85K
Ben Cera
Ben Cera@Bencera·
Polsia just raised $30M at a $250M valuation. Approaching $10M annual run rate. One Founder + AI. Zero employees. Polsia runs companies autonomously. It also ran its own fundraising. I just showed up for signatures.
English
875
491
5.7K
4.8M
Dziky💪🏿
Dziky💪🏿@dzikyDonnyMaps·
@sairahul1 Most are stuck in the “type prompt → get answer” loop. The people pulling ahead are the ones who’ve moved past surface usage into understanding the underlying mechanics, failure modes, and emergent behaviors. Usage is table stakes now. Understanding is the edge.
English
0
0
1
335
Rahul
Rahul@sairahul1·
Godfather of AI: "If you sleep well tonight, you may not have understood this lecture." This 47-minute lecture is the best thing I saw about AI in the last few months. It will definitely help you understand how it actually works and where it's going. Geoffrey Hinton built the neural networks behind every AI alive, then quit Google to warn the world about it. The part nobody wanted to hear: > AI is already developing abilities its creators didn't intend > in most cognitive tasks it's already ahead of us > the question is no longer if it surpasses us but when > the only decision left is which side of that line you're on Right now the average person opens Claude, types something, gets an answer, closes the tab. They think they're using AI. they're using maybe 10% of it. I went through his entire lecture, built a practical concepts from what he was describing. The gap won’t be between people who use AI and people who don’t. It’ll be between people who understand it and people who don’t. Start with these 20 AI concepts today 👇
Rahul@sairahul1

x.com/i/article/2057…

English
29
288
1.4K
346.5K
Dziky💪🏿
Dziky💪🏿@dzikyDonnyMaps·
@rushicrypto Most people aren’t terrified of AI itself. They’re terrified of being on the wrong side of the transition with no real backstop. The concentration of power and capital accelerating this makes the “we’ll figure it out later” approach feel reckless.
Dziky💪🏿 tweet media
English
0
0
0
25
Rushi
Rushi@rushicrypto·
Are billionaires actually insane? They’re dumping billions into AI, building data centers everywhere, laying off thousands of workers, and acting like none of this will have consequences. Everybody with a normal job can feel what’s coming. People are terrified. And there’s basically no safety net if it all collapses. It honestly feels like they’re racing toward some massive crisis while hoping we stay distracted until it’s too late.
English
620
768
4.1K
164.1K
Dziky💪🏿
Dziky💪🏿@dzikyDonnyMaps·
@danywander A lot feel like they’re selling the fantasy before the system actually works without constant babysitting. Iconic name though. You have to respect the audacity.
English
0
0
2
4.8K
Dziky💪🏿
Dziky💪🏿@dzikyDonnyMaps·
@regent0x_ The built-in commands (/compact, /plan, /review, etc.) are genuinely enough for most serious work. The best setups I’ve seen lately are the ones that got simpler, not more complicated. Less overhead = longer sessions = better output.
English
0
0
0
513
Dziky💪🏿
Dziky💪🏿@dzikyDonnyMaps·
@regent0x_ I went through the same thing. Deleted a ton of plugins. Sessions got longer, cleaner, and sharper. The native commands + proper context handling do way more than people realize. The plugin tax is real. Master what’s already there first.
English
0
0
0
110
regent0x
regent0x@regent0x_·
karpathy said it best - most people paying for claude aren't actually using claude. they're typing prompts into a $20/mo chatbox meanwhile claude code ships with built-in features that replace 90% of plugins people install and nobody knows they exist i had 23 plugins. deleted all of them. my sessions got 3x longer and my outputs got sharper watch the video then read the full breakdown below - you'll probably uninstall half your setup by tonight
regent0x@regent0x_

x.com/i/article/2057…

English
41
161
2.5K
702.4K
Dziky💪🏿
Dziky💪🏿@dzikyDonnyMaps·
@deepseek_ai At these prices they’re not competing anymore, they’re subsidizing the entire builder economy. Western frontier labs must be feeling this.
Dziky💪🏿 tweet media
English
0
0
11
3K
Dziky💪🏿
Dziky💪🏿@dzikyDonnyMaps·
@DavidOndrej1 At these prices they’re not competing anymore, they’re subsidizing the entire builder economy. Western frontier labs must be feeling this.
Dziky💪🏿 tweet media
English
0
0
0
449
Dziky💪🏿
Dziky💪🏿@dzikyDonnyMaps·
@ns123abc Discovery velocity just went parabolic. Defense is now entirely about patching speed and prioritization. Old internet foundations are about to feel it.
Dziky💪🏿 tweet media
English
0
0
0
39
NIK
NIK@ns123abc·
🚨 Anthropic just dropped the first Project Glasswing update Claude Mythos found 10,000+ critical vulnerabilities in ONE month: > Cloudflare: 2,000 bugs, 400 high/critical severity > Mozilla: 271 vulnerabilities in Firefox 150 — 10x more vulnerabilities found in Firefox 148 > UK AI Security Institute: first model to solve BOTH their cyber attack simulations end to end > at one partner bank, Mythos prevented a fraudulent $1.5M wire transfer in real time > wolfSSL: found a way to forge certificates on a crypto library used by billions of devices > scanned 1,000+ open source projects > 90.6% true positive rate after human review > maintainers are asking Anthropic to SLOW DOWN because they can’t patch fast enough > Microsoft says patch volume will “continue trending larger for some time” The bottleneck in cybersecurity is no longer finding bugs. It’s fixing them. “Progress on software security used to be limited by how quickly we could find vulnerabilities. Now it’s limited by how quickly we can patch them.”
NIK tweet mediaNIK tweet media
Anthropic@AnthropicAI

Last month we launched Project Glasswing, our collaborative AI cybersecurity initiative. Since then, we and our partners have found more than ten thousand high- or critical-severity vulnerabilities in essential software.

English
105
171
2.2K
398.1K
Dziky💪🏿
Dziky💪🏿@dzikyDonnyMaps·
@GoogleAIStudio The gap between idea → working multiplayer prototype is collapsing fast. Curious how this stacks up against Antigravity + Cursor workflows for serious builds.
English
0
0
0
17
Google AI Studio
Google AI Studio@GoogleAIStudio·
vibe coding in AI Studio just got a major upgrade 🚀 • multiplayer: build real-time games & tools • real services: connect live data • persistent builds: close the tab, it keeps working • pro UI: shadcn, Framer Motion & npm support we can't wait to see what you build!
English
300
581
5.6K
4.6M
Dziky💪🏿
Dziky💪🏿@dzikyDonnyMaps·
Takes from video • Start with clear planning mode (don’t one-shot complex tasks). • Use CLAUDE.md (or equivalent) for persistent project rules, conventions, and constraints. • Leverage sub-agents / parallel agents for speed (e.g., one for implementation, others for review/testing). • Advanced techniques: • Specific prompts and shortcuts for better control. • Settings files for team consistency (pre-approve safe commands, block risky ones). • Hooks and structured outputs to make agents more reliable and autonomous. • Handling large codebases with smart context retrieval. • Production realities: Where things break (hallucinations, context drift, permission issues) and how to fix them with better prompting, planning, and review patterns.
English
1
0
2
98
Rohit
Rohit@ai_rohitt·
🚨 Anthropic just showed a 27-minute workshop on how to actually do prompts for Claude. Taught by the people who built it. Free. No registration. No paywall. I've seen $300 courses that don't cover what they teach in the first 8 minutes. Watch it and bookmark it now.
English
43
643
3.5K
485.9K
Dziky💪🏿
Dziky💪🏿@dzikyDonnyMaps·
@cursor_ai 90% off for the long weekend is a nice nudge to actually experiment. The real test will be how well it holds up in longer, multi-step agent workflows vs just raw model calls.
English
0
0
0
27
Cursor
Cursor@cursor_ai·
With the Cursor SDK, you can build your own agents with Composer 2.5. It's now available in Python and TypeScript. This long weekend, Composer usage is 90% off in the SDK. We're excited to see what you build!
English
125
186
2.5K
487.6K
Dziky💪🏿
Dziky💪🏿@dzikyDonnyMaps·
@loffredojeremy They want natural behavior patterns, not staged demos. The manual memory card collection in 2026 is the funniest detail though. Either privacy is fully dead or this is peak viral folklore.
English
0
1
23
4.6K
Jeremy Loffredo
Jeremy Loffredo@loffredojeremy·
I just ran into a guy I know in NYC who said he’s doing a temporary gig for OpenAI. According to him, OpenAI is paying hundreds of people and families in New York to install 360-degree cameras throughout their homes that record virtually everything. Vacuuming, washing dishes, cooking, and everything else. He said his job is to go around collecting the memory cards and replacing them with new ones. According to him, OpenAI told workers like him that the recordings are being used to help develop a smart home device. But he said the strange part is that all of the people supervising the project are behavioral psychologists.
English
340
2.3K
20.5K
3.3M
Kirill
Kirill@kirillk_web3·
Anthropic CEO after watching a $20B Chinese AI founder hand out the exact architecture that beats Claude for free in 40 minutes
Kirill@kirillk_web3

instead of watching 2 hours of Netflix tonight, watch this 40-minute masterclass from the founder of a $20B China AI company it's the clearest explanation I've seen of how Agent Swarms and AI systems actually work at scale useful whether you've never built an agent in your life or have been using Claude every day for the past year I took the key ideas and turned them into a practical guide on how to actually build with Kimi find it below

English
64
680
6.9K
2.8M
Kirill
Kirill@kirillk_web3·
instead of watching 2 hours of Netflix tonight, watch this 40-minute masterclass from the founder of a $20B China AI company it's the clearest explanation I've seen of how Agent Swarms and AI systems actually work at scale useful whether you've never built an agent in your life or have been using Claude every day for the past year I took the key ideas and turned them into a practical guide on how to actually build with Kimi find it below
Kirill@kirillk_web3

x.com/i/article/2056…

English
68
1.7K
12.7K
10.3M

Keşfet

@shwarmadev @eng_khairallah1 @Bencera @sairahul1 @rushicrypto @danywander @regent0x_ @deepseek_ai