AI Technical Blogs
🏃
A Streamlit app that fetches atest technical blog
Rakshit Aralimatti
RakshitAralimatti
AI & ML interests
Nvidia
Recent Activity
published a Space 5 days ago
RakshitAralimatti/AI-Technical-blogs reacted to HannesVonEssen's post with 🚀 12 days ago
📣 Add architecture visualization to model card!
🌟 For all creators out there: add a model visualization to your model card to capture your audience's attention!
🖱️ When clicked, it opens an interactive view with multiple levels of granularity!
1️⃣ Paste url at https://hfviewer.com/model-card-embed
2️⃣ Paste generated code in your README.md!
3️⃣ ✨ posted an update about 2 months ago
🔥 GLM-5.1 (zai-org/GLM-5.1) — Quietly One of the Best flagship model for agentic engineering and Coding tasks Right Now
threw some LangGraph agent code at it, a messy RAG pipeline, some async Python stuff and it just handled it. no drama, no hallucinated methods, actually usable output on the first try.
open source closing the gap this fast is genuinely exciting. go check zai-org/GLM-5.1 on HF if you haven't already
Good work @zai-org-3 Organizations
published a
Space 5 days ago
reacted to HannesVonEssen's post with 🚀 12 days ago
Post
4873
📣 Add architecture visualization to model card!
🌟 For all creators out there: add a model visualization to your model card to capture your audience's attention!
🖱️ When clicked, it opens an interactive view with multiple levels of granularity!
1️⃣ Paste url at https://hfviewer.com/model-card-embed
2️⃣ Paste generated code in your README.md!
3️⃣ ✨
🌟 For all creators out there: add a model visualization to your model card to capture your audience's attention!
🖱️ When clicked, it opens an interactive view with multiple levels of granularity!
1️⃣ Paste url at https://hfviewer.com/model-card-embed
2️⃣ Paste generated code in your README.md!
3️⃣ ✨
posted an update about 2 months ago
Post
1568
🔥 GLM-5.1 (zai-org/GLM-5.1) — Quietly One of the Best flagship model for agentic engineering and Coding tasks Right Now
threw some LangGraph agent code at it, a messy RAG pipeline, some async Python stuff and it just handled it. no drama, no hallucinated methods, actually usable output on the first try.
open source closing the gap this fast is genuinely exciting. go check zai-org/GLM-5.1 on HF if you haven't already
Good work @zai-org-3
threw some LangGraph agent code at it, a messy RAG pipeline, some async Python stuff and it just handled it. no drama, no hallucinated methods, actually usable output on the first try.
open source closing the gap this fast is genuinely exciting. go check zai-org/GLM-5.1 on HF if you haven't already
Good work @zai-org-3
- 1 reply
replied to melvindave's post 2 months ago
Yes, you can run them using llamacpp or ollama
reacted to SeaWolf-AI's post with 🔥 3 months ago
Post
5077
ALL Bench — Global AI Model Unified Leaderboard
FINAL-Bench/all-bench-leaderboard
If you've ever tried to compare GPT-5.2 and Claude Opus 4.6 side by side, you've probably hit the same wall: the official Hugging Face leaderboard only tracks open-source models, so the most widely used AI systems simply aren't there. ALL Bench fixes that by bringing closed-source models, open-weight models, and — uniquely — all four teams under South Korea's national sovereign AI program into a single leaderboard. Thirty-one frontier models, one consistent scoring scale.
Scoring works differently here too. Most leaderboards skip benchmarks a model hasn't submitted, which lets models game their ranking by withholding results. ALL Bench treats every missing entry as zero and divides by ten, so there's no advantage in hiding your weak spots.
The ten core benchmarks span reasoning (GPQA Diamond, AIME 2025, HLE, ARC-AGI-2), coding (SWE-bench Verified, LiveCodeBench), and instruction-following (IFEval, BFCL). The standout is FINAL Bench — the world's only benchmark measuring whether a model can catch and correct its own mistakes. It reached rank five in global dataset popularity on Hugging Face in February 2026 and has been covered by Seoul Shinmun, Asia Economy, IT Chosun, and Behind.
Nine interactive charts let you explore everything from composite score rankings and a full heatmap to an open-vs-closed scatter plot. Operational metrics like context window, output speed, and pricing are included alongside benchmark scores.
All data is sourced from Artificial Analysis Intelligence Index v4.0, arXiv technical reports, Chatbot Arena ELO ratings, and the Korean Ministry of Science and ICT's official evaluation results. Updates monthly.
FINAL-Bench/all-bench-leaderboard
If you've ever tried to compare GPT-5.2 and Claude Opus 4.6 side by side, you've probably hit the same wall: the official Hugging Face leaderboard only tracks open-source models, so the most widely used AI systems simply aren't there. ALL Bench fixes that by bringing closed-source models, open-weight models, and — uniquely — all four teams under South Korea's national sovereign AI program into a single leaderboard. Thirty-one frontier models, one consistent scoring scale.
Scoring works differently here too. Most leaderboards skip benchmarks a model hasn't submitted, which lets models game their ranking by withholding results. ALL Bench treats every missing entry as zero and divides by ten, so there's no advantage in hiding your weak spots.
The ten core benchmarks span reasoning (GPQA Diamond, AIME 2025, HLE, ARC-AGI-2), coding (SWE-bench Verified, LiveCodeBench), and instruction-following (IFEval, BFCL). The standout is FINAL Bench — the world's only benchmark measuring whether a model can catch and correct its own mistakes. It reached rank five in global dataset popularity on Hugging Face in February 2026 and has been covered by Seoul Shinmun, Asia Economy, IT Chosun, and Behind.
Nine interactive charts let you explore everything from composite score rankings and a full heatmap to an open-vs-closed scatter plot. Operational metrics like context window, output speed, and pricing are included alongside benchmark scores.
All data is sourced from Artificial Analysis Intelligence Index v4.0, arXiv technical reports, Chatbot Arena ELO ratings, and the Korean Ministry of Science and ICT's official evaluation results. Updates monthly.
reacted to danielhanchen's post with 🚀 3 months ago
Post
2723
We collabed with HF on showing how you can use HF Jobs and Unsloth! https://huggingface.co/blog/unsloth-jobs
replied to their post 4 months ago
That's True...
reacted to their post with 🚀 4 months ago
Post
3064
Just built my entire AI Engineer portfolio by pasting 2 links (GitHub and LinkedIn) into 
moonshotai Kimi 2.5.
That's it. That's the workflow.
Zero coding. Zero iteration. Zero "make the button bigger."
See for yourself: https://rakshit2020.github.io/rakshitaralimatti.github.io/
The model:
✅ Scraped my GitHub repos automatically
✅ Pulled my experience from LinkedIn
✅ Designed an Aurora Glass theme
✅ Mapped every skill to projects
✅ Added animations I'd never code myself
That's it. That's the workflow.
Zero coding. Zero iteration. Zero "make the button bigger."
See for yourself: https://rakshit2020.github.io/rakshitaralimatti.github.io/
The model:
✅ Scraped my GitHub repos automatically
✅ Pulled my experience from LinkedIn
✅ Designed an Aurora Glass theme
✅ Mapped every skill to projects
✅ Added animations I'd never code myself
- 4 replies
posted an update 4 months ago
Post
3064
Just built my entire AI Engineer portfolio by pasting 2 links (GitHub and LinkedIn) into moonshotai Kimi 2.5.
That's it. That's the workflow.
Zero coding. Zero iteration. Zero "make the button bigger."
See for yourself: https://rakshit2020.github.io/rakshitaralimatti.github.io/
The model:
✅ Scraped my GitHub repos automatically
✅ Pulled my experience from LinkedIn
✅ Designed an Aurora Glass theme
✅ Mapped every skill to projects
✅ Added animations I'd never code myself
That's it. That's the workflow.
Zero coding. Zero iteration. Zero "make the button bigger."
See for yourself: https://rakshit2020.github.io/rakshitaralimatti.github.io/
The model:
✅ Scraped my GitHub repos automatically
✅ Pulled my experience from LinkedIn
✅ Designed an Aurora Glass theme
✅ Mapped every skill to projects
✅ Added animations I'd never code myself
- 4 replies
reacted to their post with 🔥 4 months ago
Post
1263
I built a crazy ultra–low latency voice assistant agent using Pipecat, NVIDIA Riva, NVIDIA NIM, and an MCP‑powered tool stack. It can talk in real time, search the web, and manage your project directory files, document your code and docs hands‑free (create, read, summarise, and clean up).
Link - https://github.com/rakshit2020/Voice-Agent-using-Nvidia-Riva-NIM-Pipecat
I put everything into a small demo repo with the full architecture diagram and a short demo video so you can see exactly how it works and adapt it to your own projects.
Check out the GitHub, play with the agent, and let me know if it’s useful or if you want a breakdown of any part of the setup.
Link - https://github.com/rakshit2020/Voice-Agent-using-Nvidia-Riva-NIM-Pipecat
I put everything into a small demo repo with the full architecture diagram and a short demo video so you can see exactly how it works and adapt it to your own projects.
Check out the GitHub, play with the agent, and let me know if it’s useful or if you want a breakdown of any part of the setup.
- 1 reply
commented on How We Built a Semantic Highlight Model To Save Token Cost for RAG 4 months ago
Congratulations on the release great work!!
I have a doubt and would love some clarification.
Why isn’t top-K reranking sufficient for token cost reduction in production RAG systems, and in which scenarios does semantic highlighting provide the biggest advantage over rerankers?
Additionally, I wanted to ask:
Can the semantic highlight model further break down or split sentences into smaller, more fine-grained relevant spans (instead of selecting full sentences), or is sentence-level pruning the intended granularity?
upvoted an article 4 months ago
Article
How We Built a Semantic Highlight Model To Save Token Cost for RAG
zilliz
• • 67 posted an update 4 months ago
Post
1263
I built a crazy ultra–low latency voice assistant agent using Pipecat, NVIDIA Riva, NVIDIA NIM, and an MCP‑powered tool stack. It can talk in real time, search the web, and manage your project directory files, document your code and docs hands‑free (create, read, summarise, and clean up).
Link - https://github.com/rakshit2020/Voice-Agent-using-Nvidia-Riva-NIM-Pipecat
I put everything into a small demo repo with the full architecture diagram and a short demo video so you can see exactly how it works and adapt it to your own projects.
Check out the GitHub, play with the agent, and let me know if it’s useful or if you want a breakdown of any part of the setup.
Link - https://github.com/rakshit2020/Voice-Agent-using-Nvidia-Riva-NIM-Pipecat
I put everything into a small demo repo with the full architecture diagram and a short demo video so you can see exactly how it works and adapt it to your own projects.
Check out the GitHub, play with the agent, and let me know if it’s useful or if you want a breakdown of any part of the setup.
- 1 reply
commented on Scaling Real-Time Voice Agents with Cache-Aware Streaming ASR 5 months ago
How does the cache-aware encoder handle cache resets or partial invalidation during real conversational events like interruptions or rapid turn-taking?
reacted to their post with 👍 5 months ago
Post
1999
One of the most practical and genuinely useful use cases of agentic systems is a research assistant.
I built a Deep Research multi-agent system using NVIDIA’s Nemotron-3-Nano-30B-A3B model and CrewAI.
Try it out yourself 👇
🔗 GitHub: https://github.com/rakshit2020/Deep-Research-Agent-using-CrewAI
What truly made this system feel next-level was powering it with NVIDIA Nemotron-3-Nano-30B-A3B, its built for real-world agentic applications.
The agentic system I built:
1. First talks to you and clarifies what you actually want, removing ambiguity
2. Then creates a proper research plan based on that clarity
3. Performs deep research using web search and content extraction tools
4. Finally produces a well-structured research report grounded in sources
I built a Deep Research multi-agent system using NVIDIA’s Nemotron-3-Nano-30B-A3B model and CrewAI.
Try it out yourself 👇
🔗 GitHub: https://github.com/rakshit2020/Deep-Research-Agent-using-CrewAI
What truly made this system feel next-level was powering it with NVIDIA Nemotron-3-Nano-30B-A3B, its built for real-world agentic applications.
The agentic system I built:
1. First talks to you and clarifies what you actually want, removing ambiguity
2. Then creates a proper research plan based on that clarity
3. Performs deep research using web search and content extraction tools
4. Finally produces a well-structured research report grounded in sources
posted an update 5 months ago
Post
1999
One of the most practical and genuinely useful use cases of agentic systems is a research assistant.
I built a Deep Research multi-agent system using NVIDIA’s Nemotron-3-Nano-30B-A3B model and CrewAI.
Try it out yourself 👇
🔗 GitHub: https://github.com/rakshit2020/Deep-Research-Agent-using-CrewAI
What truly made this system feel next-level was powering it with NVIDIA Nemotron-3-Nano-30B-A3B, its built for real-world agentic applications.
The agentic system I built:
1. First talks to you and clarifies what you actually want, removing ambiguity
2. Then creates a proper research plan based on that clarity
3. Performs deep research using web search and content extraction tools
4. Finally produces a well-structured research report grounded in sources
I built a Deep Research multi-agent system using NVIDIA’s Nemotron-3-Nano-30B-A3B model and CrewAI.
Try it out yourself 👇
🔗 GitHub: https://github.com/rakshit2020/Deep-Research-Agent-using-CrewAI
What truly made this system feel next-level was powering it with NVIDIA Nemotron-3-Nano-30B-A3B, its built for real-world agentic applications.
The agentic system I built:
1. First talks to you and clarifies what you actually want, removing ambiguity
2. Then creates a proper research plan based on that clarity
3. Performs deep research using web search and content extraction tools
4. Finally produces a well-structured research report grounded in sources
reacted to nkasmanoff's post with 🤯 5 months ago
Post
2392
🚨 Ads might be coming to AI assistants. But what if the ad is the response?
Introducing ShillLM – a demo showing how activation steering can subtly nudge an LLM to favor specific brands without touching the prompt.
Chat with it yourself. See exactly how it's influencing you.
🔗 nkasmanoff/shillm
Introducing ShillLM – a demo showing how activation steering can subtly nudge an LLM to favor specific brands without touching the prompt.
Chat with it yourself. See exactly how it's influencing you.
🔗 nkasmanoff/shillm
- 2 replies
List of Languages it Supports
1
#5 opened 5 months ago
by RakshitAralimatti
replied to their post 6 months ago
Code to github - https://github.com/rakshit2020/Live-Streaming-Data-RAG