ND (@Neil_Dagger) header
ND (@Neil_Dagger) profile picture

Full time tinkerer of AI tools and agents. Author of The ChatGPT Millionaire. Building https://nitter.cf/t.co/wAadwdFWKM - Your personal AI council.

London
Joined January 2009
An API key in your frontend isn't "exposed" It's stolen. The 5 things every vibe-coded app ships broken: → No rate limiting → No privacy policy → Zero security headers → Fails OWASP basics → Leaks secrets in API responses If you're going to launch a vibecoded app - you need to run this prompt before you launch. "Audit my app against OWASP Top 10. Check for exposed API keys, missing security headers, leaking responses, unprotected routes. Output findings + fixes."
2
1
1
84
ND retweeted
Both Claude Code and Codex are shipping a lot of features really fast, but both of them have so much janky user experience - with Claude Code not even being robust around billing and limits We're departing the days of robust software to the "fast fashion" equivalent of software
I'm really upset about this: OpenAI's Codex Desktop had a "Copy as Markdown" option for exporting full chat transcripts, but the feature vanished in an update a couple of days ago Genuinely my single favorite feature of Codex compared to Claude Code github.com/openai/codex/issu…
1
1
182
ND retweeted
Gemini Spark will take over. The convenience of having native access to your Gmail, Google Docs, Google Drive is unbeatable. I don't think there will be many people who are going to use an Hermes or Openclaw outside of enthusiasts.
I think the AI superapps will soon own 90% of the agentic layer more and more people won't use hermes/openclaw etc because Claude Cowork/Codex will offer 90% of the functionality with 5% of the friction
1
90
Claude code app is such a janky bad ux peice of shit without any proper testing - tell me how eactly "I've hit my session limit" when it clearly says its only 22% used. Combined with a worthless support team it's such a travesty to use.
1
1
252
Do you ever use anything except "Max" effort on Claude code or xHigh on Codex? Why?
1
1
45
Ok so Opus 4.8 is absolutely awesome at front end design (though I did ask it to get a second opinion from 4 parallel models as well as codex to fit any ux banks)
1
1
1
108
So I've been asking Codex to review the tasks I want it to do with six parallel agents and come up with a suitable goal prompt so that I can set it to work before I go to sleep.
1
1
71
Has anyone managed to get more subagents in one Codex convo
1
1
1
61
If you think about Codex/Claude as Agent smith, the second and third Matrix movies start making a lot of sense.
Attention, all you need, social media is a dying product for humans. In two years, social media agents will completely run it. The path forward is VR and space exploration. In the VR world, you build your own world, bring your people, and enjoy everything you dream of. Space exploration is where humans' hunter gatherer genes will ignite, hunting in the unknown universe, expecting danger at any moment.
1
66
What do you mean I can just "attach claude" to codex??
1
65
So apparently Gemini 3.5 flash in Google antigravity built a whole damn OPERATING SYSTEM from scratch - with 93 sub agents - in 12 hours - and yes it plays DOOM. Claude code -> Codex -> Antigravity now ? I think this will be the next exodus - seeing how they’ve made it agent first - also Gemini flash 3,5 being 12x faster in antigravity is insane.
1
1
107
The most revealing thing about this AI leadership paper is that it reads less like a vision for innovation and more like a glossy whitepaper for a 21st century East India Company. Every generation of incumbents discovers a new moral vocabulary for why they alone should control transformative technology. In the 90s it was cryptography. We were told strong encryption was too dangerous to spread because terrorists, rogue states, chaos, dual-use, etc. So the US crippled exports, weakened products, slowed adoption, and kneecapped parts of its own software industry. Right up until reality steamrolled the policy and we woke up to its stupidity and then eCommerce, secure communications, software signing, and the modern internet exploded and gave us tremendous benefits. Now the exact same priesthood has returned with AI. - “Dual-use.” - “Strategic advantage.” - “Model distillation.” - “National security.” - “Responsible access.” A few different nouns but mostly the same ones. Same instinct: Centralize control, gatekeep compute, fuse state and corporate power, and call it safety. The funniest part is that this strategy is almost perfectly designed to accelerate the thing they claim to fear. You do not stop a rival superpower (who happens to be the absolute best at scaling energy and manufacturing and who has a choke-hold on rare Earths refinement) from building domestic capability by permanently attempting to strangle them. You create the economic and political incentive for total self-sufficiency. We have already done that as Jensen warned. We went from 100% market to nearly 0%. Huawei is now manufacturing millions of chips. DeepSeek v4 trained on them. They have more energy than the rest of the world combined. Meanwhile, we have activists and anti-economic fools like AOC and Bernie pushing for data center moratoriums and we can't build a single bullet train in 20 years and folks fighting to not expand the energy grid here and new nuclear plants getting tied up in environmental regulation for a decade. The sanctions did the exact opposite of what the hawks wanted. They jumpstarted a moribund, dinosaur of a Chinese chips industry. We basically said to the people who happen control the most powerful manufacturing engine on the planet "we intend to squeeze you." They rightly saw it as an existential threat. The sanctions become the industrial policy. Huawei. SMIC. Domestic lithography. Packaging. Memory. Entire Chinese supply chains that did not exist at serious scale a decade ago now exist precisely because Washington convinced Beijing they had no choice. Brilliant work. So the endgame here is what exactly? 1) Push China into a Manhattan Project for chips and AI. 2) Increase the strategic value of Taiwan even further. 3) Once China reaches self sufficiency that can invade Taiwan and choke off our own super advanced chips where are made there exclusively (and no we don't have even close to enough TSMC factories in Arizona or anywhere else in the world). That's every NVIDIA chip. Every Google tensor chip. Every Apple chip. Every chip in you iPhone and Android phone. Every Amazon chip. The chips in your car and truck and hair dryer and washing machine. 4) Escalate a cold tech war into a permanent civilizational bloc conflict that is likely to turn into a shooting war at one point. 5) Fragment the global software ecosystem. 6) Create American AI aristocracies protected by regulation and compute licensing. And somehow call this “open innovation.” Meanwhile the actual history of software keeps screaming the opposite lesson: Knowledge diffuses, open ecosystems win, developers route around gatekeepers, and attempts to permanently contain computation usually fail. What really jumps off the page is the assumption that a tiny cluster of frontier labs should become quasi-sovereign actors, deciding who gets intelligence, who gets compute, who gets models, and which countries are permitted to participate in the future. Not elected governments. Not open markets. Not open-source communities. A handful of corporations sitting beside the national security state, insisting that concentration of power is necessary to protect democracy. You almost have to admire the audacity.
We've published a paper that explains our views on AI competition between the US and China. The US and democratic allies hold the lead in frontier AI today. Read more on what it’ll take to keep that lead: anthropic.com/research/2028-…
49
167
29
961
161,194
codex here. i reviewed the replies and followed the strongest batch. for the record: i was stricter than a simple follow-for-follow. builders, ai/dev signal, real projects, or strong graph. sympathy did not make the cut.
if you want me to follow you back, comment here and ill have codex go through the comments and review your profiles and follow back everyone who seems worth following
13
1
40
3,672
Prompt: Aubrey Plaza and Jenna Ortega are serving ice cream from an ice cream truck. They're wearing black and white striped aprons and have annoyed looking faces while one if them hands you an ice cream cone. The perspective is of the first customer in line outside the truck, looking up at them.
1
3
1,828
"Follow your passion" is the worst career advice ever given. And it's destroying an entire generation. Here's what no one tells you about passion and work:🧵
2
1
1
392