Posts by Sajal Kanti

@Sajal Kanti

Sajal Kanti Dev

I enjoy turning ideas into working software. Most of my time is spent building, ...
Joined July 2026
993 Points • 16 Badges • 15 Connections • 15 Followers • 20 Following

Comments by Sajal Kanti

Aug 27 • Articles • 6 min read
She is standing on an empty stretch of concrete. Nothing here but cracked pavement and weeds pushing through the seams. She puts on a pair of lightweight glasses and the concrete dissolves. A porch appears in front of her — wooden steps, a rusted ra...
post-cover-25482
Aug 27 • Articles • 2 min read
Pushed Out by the Shadows For almost seven months now I have blinked less than the crippled, cramped fingers I count on my tired hands. I have howled so loud that even the sheep ignore me when I howl at the largest light in the room. “That...
Aug 27 • Articles • 1 min read
Owning your LLM and ML model infrastructure is often framed as a cost decision. But what happens when the models running on that infrastructure are part of your company’s core intellectual property? A session at RenderATL Render Atlanta about Physica...
post-cover-25456
Aug 25 • Articles • 3 min read
Introduction Cloud waste is a silent budget killer. Industry reports estimate that companies waste up to 30% of their cloud spend on idle resources, misconfigurations, and forgotten instances. For FinOps and SRE teams, this means drowning in a sea o...
post-cover-25301
Aug 25 • Articles • 1 min read
Hey devs, As agentic workflows expand from sandboxed chat into production systems and IoT hardware, prompt engineering alone isn't a sufficient safety barrier. If an agent hallucinates a payload or triggers a cascading loop, traditional error-handli...
post-cover-25300
Aug 25 • Articles • 1 min read
The OWASP Top 10 for LLM Applications is a great starting point for understanding AI security. But knowing the risks isn't enough. The real question is 𝗪𝗵𝗮𝘁 𝗱𝗼 𝘆𝗼𝘂 𝗮𝗰𝘁𝘂𝗮𝗹𝗹𝘆 𝗶𝗺𝗽𝗹𝗲𝗺𝗲𝗻𝘁 𝘁𝗼 𝗺𝗶𝘁𝗶𝗴𝗮𝘁𝗲 𝘁𝗵𝗲𝗺? When analyzing the OWASP LLM risks from an en...
post-cover-25282
Aug 21 • Articles • 6 min read
A follow-up. The previous article described what we are building. This one describes how it works in practice - and why the shift from academic tool to industrial platform matters. In a previous article, I described the architecture of a protocol a...
post-cover-24974
Aug 21 • Articles • 4 min read
I added DuckDB to my SQL playground, and it turned out to be a sandboxing problem Sharing a small build-in-public update: sqlize.onlinehttps://sqlize.online, a free tool for testing SQL queries, checking JOINs, and sharing reproducible examples, ju...
post-cover-24989
Aug 21 • Articles • 4 min read
If you generate PDFs from web pages by screenshotting them, you've probably hit this: the PDF looks perfect and is completely useless the moment you want to use the text. Ctrl+F finds nothing. You can't copy a sentence. A screen reader opens the do...
post-cover-24991
Aug 21 • Articles • 2 min read
Problem:How do I do  this "json.decoder.jsondecodeerror: expecting value: line 1 column 1 char 0"?   Solution: To summarize the conversation in the comments: There is no need to use simplejson library, the same library is included with Python as...
Aug 20 • Articles • 2 min read
Building AI Voice Agents? Here is where your architecture would break. 1. When a user can update the UI using voice 2. User clicks and speaks at the same time 3. Adding voice to legacy applications 4. Asking Agents to make a phone call You m...
post-cover-24812
Aug 20 • Articles • 3 min read
The DeepSeek Harness ecosystem is growing quickly. A search can surface desktop shells, terminal tools, interface tweaks, vision extensions, workflow helpers, and plugin registries. The hard part is not finding a name. It is understanding what that p...
Aug 20 • Articles • 4 min read
In the realm of applied data science, building a model that performs well on static datasets is a standard rite of passage. But deploying an AI to predict outcomes in a chaotic, high-variance environment-such as professional sports-is an entirely dif...
Aug 14 • Articles • 11 min read
Originally published on dev.tohttps://dev.to/namakoo/the-day-my-agent-started-having-hunches-f7o. Reposted here in full. My last post here was about curating training data for LLMs. This one is stranger: it is about giving a coding agent an involunt...
post-cover-24610
Aug 14 • Articles • 4 min read
Have you noticed something strange lately? You ask AI to build a modern website. And suddenly, your website looks like hundreds of other AI-generated websites. Blue or purple gradient. Big hero section. Rounded cards. Glassmorphism. Huge headl...
post-cover-24598
Aug 14 • Articles • 1 min read
AI VS Software Engineers Talk that AI will replace software engineers is everywhere. As a developer, I view this as evolution, not competition. AI can generate code, write documentation, create test cases, explain algorithms, find bugs, and automat...
post-cover-24609
Aug 11 • Articles • 1 min read
A business can have a good website, good reviews, and even strong Google rankings and still be almost invisible when someone asks ChatGPT or Gemini: “What’s the best service in city?” I recently looked into this problem and found that some business...
post-cover-24392
Aug 11 • Articles • 4 min read
The financial industry is changing rapidly as businesses adopt digital tools to manage transactions, customer information, reporting, compliance, and day-to-day operations. From banks and lending companies to accounting firms and fintech startups, or...
post-cover-24376
Aug 11 • Articles • 3 min read
The cause for Indexerror: index 0 is out of bounds for axis 0 with size 0 is when trying to access the first element stored inside the first dimension array. However, such a numpy array is empty and hence inaccessible. This tutorial shows an example ...
chevron_left