AI Developer | Fullstack Dev | Kelvin Dim

Tech Lead in Sydney, 12+ years of designing & building Fullstack products powered by AI, Data & People. Always building something.

[AI Developer | Fullstack Dev | Kelvin Dim @KelvinDimson]

2-0 #Australia
#WorldCup #AustraliaTurkey

[Arsenal @Arsenal]

The Arsenal. Your Premier League champions.

[Arsenal @Arsenal]

Your Class of 2025/26: Part II.

[AI Developer | Fullstack Dev | Kelvin Dim @KelvinDimson]

Another one…damn!

[News from Google @NewsFromGoogle]

The Google Threat Intelligence Group has detected the first known instance of a threat actor using an AI-developed zero-day exploit in the wild. While the attackers planned a wide-scale strike, our proactive counter-discovery may have prevented that from happening. This finding is part of our new report on AI-powered threats.

[AI Developer | Fullstack Dev | Kelvin Dim @KelvinDimson]

Things are about to really ugly, while celebrate the wins of AI, we keep forgetting that there are ugly players looking to exploit the system.
#CyberSecurity #Security #Tanstack #npm

[Socket @SocketSecurity]

Update: Socket has found 121 more compromised npm package artifacts across 84 package names, including 64 UiPath artifacts.

Combined w/ TanStack, the current known total is 205 affected npm package artifacts across enterprise automation, AI/MCP, auth, workflow, and dev tooling.

[AI Developer | Fullstack Dev | Kelvin Dim @KelvinDimson]

Anybody that claims he told an agent what to do in Claude code & went to bed and the agent produced good result is either doing automation or lying because we are still vary far from hands of agentic execution without guidance for real world production grade work.

[Martien 🇳🇱 @MartienBall]

Me every time someone I don’t even know beats cancer

[SANTAN @Santandave1]

IM RAPPING AGAIN!

[AI Developer | Fullstack Dev | Kelvin Dim @KelvinDimson]

@zan2434 @eddiejiao_obj @drewocarr Flipbook will swallow your seo… there is an exisiting tech called flipbook, but this looks amazing

[Google DeepMind @GoogleDeepMind]

Deep Research and Deep Research Max are our latest autonomous research agents powered by Gemini 3.1 Pro.

They can safely navigate both the web and your custom data, like internal docs and specialized financial information, to create professional-grade, fully cited reports. 🧵

[AI Developer | Fullstack Dev | Kelvin Dim @KelvinDimson]

@chalaska Well alit by the looks of it 😌

[AI Developer | Fullstack Dev | Kelvin Dim @KelvinDimson]

@bertona5 @k1rallik I don’t use Vercel but they offer alot more they basically are one of the few companies investing in tech echo system now, but yeah have some understanding of your vps will super important for you, agents alone is not enough.

[AI Developer | Fullstack Dev | Kelvin Dim @KelvinDimson]

@ConsciousRide Lmao… 😂😂😂😂😂😂😂😂

[AI Developer | Fullstack Dev | Kelvin Dim @KelvinDimson]

@bertona5 @k1rallik 🤦‍♂️🤦‍♂️🤦‍♂️🤦‍♂️ … so basically have no idea what is happening in your infra and you are happy to brag about it???

[AI Developer | Fullstack Dev | Kelvin Dim @KelvinDimson]

@mhp_guy This has existed for year man… its not new

[AI Developer | Fullstack Dev | Kelvin Dim @KelvinDimson]

Gout Gout just ran 19.67? 😳😳😳😳😳 … Faster than Usain Bolt?. This is insane. #Australia #AustralianAthleticsChampionship

[AI Developer | Fullstack Dev | Kelvin Dim @KelvinDimson]

@alisaqqt @atlas_cloud_ai Saw this post, signed up for api access, nearly funded my account, it was late, I went to bed by the time I woke up, model removed, I would have just been pissed cos that $100 would have been locked for nothing. At least let people know you are suspending the service.

[AI Developer | Fullstack Dev | Kelvin Dim @KelvinDimson]

@TuoyoS26091 All you new boys to the dev space just show yourselves … lol, opensource has been a thing since forever, you lot need to just keep quiet.

[AI Developer | Fullstack Dev | Kelvin Dim @KelvinDimson]

@zee_chill_dev @wikiwayne @Hartdrawss Lol… ok😂

[AI Developer | Fullstack Dev | Kelvin Dim @KelvinDimson]

@knifeineye @kaiostephens Ok memory layer is the basic principle behind RAG before models had native internet access, what you need to read up on are vector database, vector embedding and chunking strategies, a combination of these three concepts will give you a “Memory” hope it helps.