rv

3.9K posts

rv

rv

@rv24us

👨‍💻 Irresponsibly long Bitcoin| 📈 Programmer |🔗 Crypto Enthusiast since 2017 | 💎 Bitcoin Maximalist .#Bitcoin #BlockchainRevolution

Dallas, TX Katılım Haziran 2009
3.5K Takip Edilen640 Takipçiler
rv retweetledi
darkzodchi
darkzodchi@zodchiii·
Anthropic engineer showed how one person can run 5 AI agents, that code, test, review, and deploy at the same time. In 30 minutes they built the whole thing live in one session. Here's what they cover: > when to use one agent vs a full team > how to split work so agents don't step on each other > the exact framework for deciding what each agent handles that's exactly why, I put together a guide on building agent teams that actually work. full guide in the article below 👇
rody@0x_rody

x.com/i/article/2058…

English
77
530
4.1K
808.8K
rv retweetledi
Prajwal Tomar
Prajwal Tomar@PrajwalTomar_·
Codex is CRACKED at design now and I don't think people understand how BIG this is. Look at this. Design on the left. Codex shipping pixel-perfect code on the right in under 3 minutes. The whole Figma to designer to developer cycle just collapsed into a single workflow. Designers used to take this Figma file, hand it off to devs, wait 2 weeks for implementation, then spend another week fixing spacing and colors. Now Codex reads the design system, generates the screens, and ships production code while you're still in the same session. I've been testing this with every client project at my agency for the last month and it's legitimately unfair. Full breakdown in the article.
Prajwal Tomar@PrajwalTomar_

x.com/i/article/2056…

English
35
65
738
120.2K
rv retweetledi
Kappaemme
Kappaemme@Kappaemme1926·
CODEX SKILL THAT CREATES A REAL WEBSITE IN LESS THAN 10 MINUTES! I made a Codex skill that combines image generation with image-to-code. It generates visual references first, analyzes the design, then helps Codex build the actual frontend from those references instead of starting from a generic layout. I merged two workflows into one: $imagegen + $image-to-code -> generate visual website references first -> one readable image per section -> deep design analysis before coding -> typography, spacing, colors, and component extraction -> faithful frontend implementation -> avoids generic AI-looking landing pages -> useful for heroes, landing pages, portfolios, product pages, redesigns -> one-command install Install: npx --yes codex-visual-web-builder Then use it in Codex with: $visual-web-builder 100% open source. Repo in Bio.
English
17
33
419
31.5K
rv retweetledi
Elon Musk
Elon Musk@elonmusk·
ZXX
9.4K
21.5K
157.3K
57.2M
rv retweetledi
jason
jason@jxnlco·
jason from the codex team here, heres a draft on codex maxxing and the primatives i use on a daily basis jxnl.github.io/blog/writing/2… would love any feedback
English
151
217
3.5K
379.4K
rv retweetledi
Elon Musk
Elon Musk@elonmusk·
Where will AI be in 1, 2 or 3 years?
English
7K
14.6K
110.7K
40M
rv retweetledi
Dan McAteer
Dan McAteer@daniel_mac8·
GPT-5.5 + Codex in /goal mode just ran an end-to-end mech-interp experiment on my computer. In ~2 hours it: - read the Natural Language Autoencoders paper/repo/checkpoints - designed a 120-prompt dataset + scoring rubric - set up my Nvidia GB10 box over SSH with CUDA/PyTorch - debugged the NLA inference path - wrote activation extraction, decoding, scoring, and analysis scripts - ran smoke tests + the full experiment - debugged failures and reran - produced a final report, figures, and HTML writeup My rough estimate with GPT-5.5: this would take a careful human researcher 25-45 focused hours. With unfamiliar infra, maybe 60-80. So call it a 10-40x speedup on a compact, real research workflow. Absolutely amazing. Jack Clark now puts 60%+ odds on no-human-involved AI R&D by the end of 2028. OpenAI is tracking toward intern-level research assistants in 2026 and fully automated researchers by 2028. Today’s models can already compress days of experiment tasks into an afternoon. What happens when 2028-level models are doing this 24/7, in parallel, across thousands of research directions? That’s the curve we're on.
Dan McAteer tweet media
English
6
12
63
11.1K
rv retweetledi
Greg Brockman
Greg Brockman@gdb·
codex for improving computational complexity
Kappaemme@Kappaemme1926

CODEX SKILL THAT FINDS COMPLEXITY HOTSPOTS IN YOUR CODEBASE! I made a Codex skill that analyzes your codebase and reports where performance can be improved safely. Scan your project while Codex checks loops, repeated lookups, render-heavy code, N+1 patterns, and places where complexity can potentially be reduced without breaking behavior. -> codebase complexity analysis -> O(n²), O(n*m), repeated scan detection -> before/after complexity estimates -> safe optimization suggestions -> risk level + tests needed -> report-only mode by default -> one-command install Install: npx --yes codex-complexity-optimizer 100% open source. Repo in Bio.

English
59
112
1.8K
327.3K
rv retweetledi
Kappaemme
Kappaemme@Kappaemme1926·
CODEX SKILL THAT FINDS COMPLEXITY HOTSPOTS IN YOUR CODEBASE! I made a Codex skill that analyzes your codebase and reports where performance can be improved safely. Scan your project while Codex checks loops, repeated lookups, render-heavy code, N+1 patterns, and places where complexity can potentially be reduced without breaking behavior. -> codebase complexity analysis -> O(n²), O(n*m), repeated scan detection -> before/after complexity estimates -> safe optimization suggestions -> risk level + tests needed -> report-only mode by default -> one-command install Install: npx --yes codex-complexity-optimizer 100% open source. Repo in Bio.
English
39
99
1.3K
294.2K
rv
rv@rv24us·
ZXX
0
0
0
12
rv retweetledi
Alvaro Cintas
Alvaro Cintas@dr_cintas·
Obsidian CEO personally wrote the official Agent Skills for his own app 🤯 These are 5 skills that fix every layer agents get wrong: → obsidian-markdown (wikilinks, callouts, embeds, frontmatter) → obsidian-bases (database views with filters, formulas, aggregations) → json-canvas (visual canvases linked to your notes) → obsidian-cli (search, create, manage tasks from the terminal) → defuddle (clean markdown from any web page) MIT licensed. Works with Claude Code, Codex CLI, OpenCode.
Alvaro Cintas tweet media
English
29
146
1.1K
53.5K
rv retweetledi
Hasan Toor
Hasan Toor@hasantoxr·
Holy shit... someone made it work that I can integrate a social media manager inside Claude It's called OmniSocials and it lets Claude draft, schedule, and publish to 10 platforms from a single command. No Hootsuite. No Buffer. No $200/seat pricing. Here's everything you need to know: 👇
English
49
117
1.4K
241K
rv retweetledi
Peter Steinberger 🦞
Peter Steinberger 🦞@steipete·
Wrote a skill that runs codex /review in a loop until there's no booboos anymore. Caveat: It won't fix system architecture for ya, so you still need BRAIN as master model. github.com/steipete/agent…
English
127
153
2.7K
398.6K
rv retweetledi
Miles Deutscher
Miles Deutscher@milesdeutscher·
Anthropic just automated 99% of legal roles. Claude for Legal is live now - and it's a marketplace with DOZENS of agents trained on legal roles. Review agents, policy drafters, NDA agents & much more. Can't believe this is public. github.com/anthropics/cla…
English
118
303
2.3K
401.8K
rv retweetledi
Miles Deutscher
Miles Deutscher@milesdeutscher·
/goal is f*cking insane. You can literally turn your AI agents into 24/7 employees that work for HOURS with zero manual intervention. This has to be the most powerful AI feature release of the month. If you try one thing in AI this week, make it this.
Miles Deutscher tweet media
AI Edge@aiedge_

x.com/i/article/2054…

English
131
379
3.8K
775K
rv retweetledi
klöss
klöss@kloss_xyz·
been building a list of the best /goal use cases. here’s 23 you can use: 1. complex refactors 2. architecture cleanup 3. auth flow consolidation 4. state management consolidation 5. SDK wrapper consolidation 6. npm supply chain hardening 7. design system enforcement 8. component library standardization 9. typescript strictness fixes 10. test suite hardening 11. CI/CD pipeline triage 12. dependency upgrade migrations 13. schema migration safety review 14. routing/navigation refactor 15. performance optimization pass 16. accessibility audit/fix pass 17. security audit/remediation 18. error handling standardization 19. internationalization/localization wiring 20. platform migration (web/iOS/Android) 21. documentation generation 22. onboarding/architecture map creation 23. monorepo restructuring /goal is the closest thing we have to a senior engineer that never gets tired… and it works in Codex, Claude, and Hermes too. what's missing from this list? I’ll add it
klöss tweet media
klöss@kloss_xyz

/goal is the best command in Codex, Claude Code, and Hermes right now. And most are using it wrong. They write "make no mistakes". And pray. Here's how to structure yours for a mission, to rank your uncertainties before acting, to kill scope creep, and to close every loop other prompts leave open. /goal prompt [structure below] GOAL: CONTEXT: CONSTRAINTS: PRIORITY: (optional) 1. 2. 3. PLAN: DONE WHEN: VERIFY: OUTPUT: STOP RULES:

English
49
101
1.2K
119.2K
rv retweetledi
Mario Nawfal
Mario Nawfal@MarioNawfal·
xAI is building a native desktop coding app called Grok Build. GitHub Copilot and JetBrains have dominated this space for years. Grok just showed up to compete on their turf. xAI is going after the IDE market directly.
Mario Nawfal@MarioNawfal

🇺🇸 xAI was bleeding cash on frontier compute while watching all the real AI money flow into enterprise and coding tools it couldn't crack. The Anthropic deal fixes that. Elon keeps a frontier model company without the 9-figure CapEx hanging over his head. David Sacks put it plainly: Lease the capacity, skip the commitment. Smart move. The AI race is increasingly about who survives the economics, not just who builds the best model. @elonmusk @xAIMemphis

English
48
51
695
107.9K

Keşfet

@jack @elonmusk @BarackObama @taylorswift13 @cristiano @BillGates @NASA @nikifrancismediavine