Shashi Kumar
@ai_ml_architect
Followers
747
Following
45K
Media
3K
Statuses
24K
Software Architect. Amateur Photographer. Technology Aficionado. Gadget Geek.
ÜT: 17.499038,78.412048
Joined October 2008
I had quite the showdown with an AI over a Black Friday deal. Can you top that? 🤣 @Kimi_Moonshot Check it out here: https://t.co/1f3UJu9VVv
0
0
0
Claim $20 FREE credits + 7 days of automated posting: OSTLF2Z7C8 OSD5796MX2 OSX8KZU63Z OS1JTQYE0M OSM6YAXRJU
0
0
0
⚡️Built in n8n — Automations on Autopilotlll 🤖Scrape + repurpose viral content ✍️Rewrite / GPT-4o 🎥Auto-generate video 🎬Add caption & edit 📤Post to 9+ platforms in 1 click To get the guide FREE?👇 🔁Like+RT 💬Reply“N8N” 📩Ensure to follow me ( @davidwillam33 ) So i can DM
363
244
473
I just joined the Traviflow waitlist! They're launching soon, and early supporters get lifetime free access. Check it out!
traviflow.com
Plan epic group trips with friends & family using Traviflow's collaborative travel platform. Create shared itineraries, split expenses, get AI travel suggestions, and build your travel passport with...
0
0
0
OpenAI is pushing for a change in how we evaluate models, suggesting that we should penalize overly confident mistakes while rewarding uncertainty in responses. They found that this approach helped reduce hallucinations in the GPT-5-thinking-mini from 75% down to 26%. However,
0
0
0
In a recent study by OpenAI, researchers found that large language models (LLMs) tend to hallucinate because of the way they're trained and evaluated. The current methods favor making guesses rather than showing uncertainty. These hallucinations often occur during the
1
0
0
OpenAI Study Investigates the Causes of LLM Hallucinations and Potential Solutions via @dailydotdev
https://t.co/P3V9rfV26j
#OpenAI #LLMs #Hallucinations
app.daily.dev
OpenAI research identifies that LLM hallucinations stem from training methods that reward guessing over expressing uncertainty. Standard evaluation metrics prioritize accuracy and penalize abstenti...
1
1
2
Check out my latest article: AI-powered ‘Vibe Coding’: The Fast Track to Getting Fired 😬 https://t.co/OwscQt0SxR via @LinkedIn
linkedin.com
Some developers thought AI coding assistants meant they could stop learning, stop debugging, and just “vibe” their way through code. But here’s the harsh reality: AI often spits out buggy functions...
0
0
0
Hey guys! I discovered this creator platform to build and run ComfyUI in the browser faster and easier, with one-click launch and no installs. https://t.co/ttX6731uo1
#FloYo #AI #ComfyUI #NoCode #Productivity
floyo.ai
Floyo brings ComfyUI to your browser: find & launch open-source workflows in seconds, zero setup, free building, and creative freedom without limits.
0
0
1
AWS ML Engineer Crash Course View my verified achievement from @oreillymedia. https://t.co/seBf2tEou0 via @credly
credly.com
The holder of this badge has completed the following course by Pearson. The holder of this badge is capable of designing, deploying, and monitoring machine learning solutions in AWS, making them an...
0
0
0
AI Apps with SLMs View my verified achievement from @oreillymedia. https://t.co/H0LYmA8NTv via @credly
credly.com
The holder of this badge has completed the following course by O'Reilly Media, Inc. The holder of this badge is capable of understanding and leveraging small language models (SLMs) like Llama 3.2,...
0
0
0
AI Agents with MCP View my verified achievement from @oreillymedia. https://t.co/Ta2EcJZLmh via @credly
credly.com
The holder of this badge has completed the following course by O'Reilly Media, Inc. The holder of this badge is capable of creating AI agents that can seamlessly integrate with external systems using...
0
0
0
🎉 Thrilled to share that I’ve just completed the Hazelcast Platform Advanced Workshop badge! View my verified achievement from @hazelcast. https://t.co/3I03gAe4CO via @credly
#Hazelcast #InMemoryComputing #DataGrids #FinancialServices #LowLatency
credly.com
Credential holders have deepened their expertise in distributed caching and computing with Hazelcast Platform. They now have practical knowledge of applying Hazelcast Platform in real-world scenarios...
0
0
1
Wow! I have just got my new certificate in Dremio-Powered AI Agents. See it for yourself! https://t.co/DE8sOyJQLX
https://t.co/XeLOn9UXFz
#Dremio #AIAgents
university.dremio.com
A hands-on guide to powering AI agents with Dremio by Alex Merced, co-author of "Apache Iceberg: The Definitive Guide" published by O'Reilly.
0
0
2
I just registered a .cloud domain ⛅️✨ @Porkbun for $18.82! Get your own at https://t.co/zO0TQZU0uz
@getdotcloud ☁️ #dotcloud
porkbun.com
The .Cloud Domain - Smart for Modern BusinessModern businesses all over the world have embraced the .cloud domain extension, including forward-thinking small businesses, rising startups, and establ...
0
0
1
Need help studying for your AWS, CompTIA, Azure, Google Cloud, and NVIDIA certification exams? Then this latest test and prep bundle from Humble Bundle is for you! https://t.co/nvJTdaDRNC via @humble
humblebundle.com
Need help studying for your AWS, CompTIA, Azure, Google Cloud, and NVIDIA certification exams? Then our latest test and prep bundle is for you!
0
0
1
Perplexity tackled the challenge of transferring non-contiguous GPU memory across AWS P5 instances, achieving 97.1% of the 3200 Gbps bandwidth. Using RDMA and EFA, they bypassed CPU bottlenecks for direct GPU-GPU transfers. Key optimizations included operation queuing,
github.com
Contribute to perplexityai/libfabric-efa-demo development by creating an account on GitHub.
0
0
1