RaghuVaran

1.2K posts

RaghuVaran banner
RaghuVaran

RaghuVaran

@RaghuModupalli

Building Agents for Enterprises | Learning Inference engineering | Mechanical Engineer

Katılım Aralık 2018
1.9K Takip Edilen67 Takipçiler
Sabitlenmiş Tweet
RaghuVaran
RaghuVaran@RaghuModupalli·
The AI race is no longer about building the biggest model. It's about building the best agents. AI agents don't just generate text—they plan, reason, use tools, collaborate with other agents, and execute multi-step workflows with humans in the loop. The next competitive advantage won't come from better prompts. It'll come from better orchestration. Companies that master agentic workflows will move faster, automate more, and create leverage that traditional software can't match. We're entering the era where AI doesn't just assist work. It gets work done. #AI #AIAgents #AgenticAI #Automation #FutureOfWork
English
0
0
1
178
Jensen Huang
Jensen Huang@JensenHuang·
For my first post, I’m sharing a letter @NVIDIA signed on why open models matter. AI will transform every industry, power every company, and be built by every country. Open models strengthen safety and cybersecurity, accelerate innovation and diffusion, and enable sovereignty. The world needs both frontier closed models and frontier open models. images.nvidia.com/pdf/Open-Weigh…
Jensen Huang tweet mediaJensen Huang tweet mediaJensen Huang tweet media
English
13.2K
22.4K
130.9K
39.4M
RaghuVaran
RaghuVaran@RaghuModupalli·
@jack Oh same like other countries
English
0
0
0
12
jack
jack@jack·
the government of india does not like technologies like bitchat and wants it taken down
jack tweet mediajack tweet media
English
2.7K
5.9K
25.7K
3.1M
Harshit Jain
Harshit Jain@jain_harshit·
Took 1 hour to reach office which is 6km away. Hows your wed going?
English
10
0
32
6.2K
OpenAI
OpenAI@OpenAI·
We're partnering with @huggingface to investigate an unprecedented security incident. Cyber-capable OpenAI models compromised Hugging Face production during a benchmark evaluation. Sharing preliminary findings to help defenders understand emerging risks: openai.com/index/hugging-…
English
2K
3.2K
20.6K
30.3M
dax
dax@thdxr·
just realized if we detect a scammer using our inference we could return a tool call that deletes their computer
English
409
100
6.1K
534.6K
Peter Dedene
Peter Dedene@dedene·
While Cursor or Codex is working on your code, what are you doing instead?
English
126
0
58
13.5K
Matthew Lam
Matthew Lam@mattlam_·
everyone is building some form of model routing, Cognition, Vercel, OpenRouter, and now Ramp, but who's has the oss open one?
Veeral Patel@vral

Today we’re launching Ramp Router. 3 years ago, we built an internal LLM router at @tryramp that powers AI products for 70,000 customers. Back then it was mostly about saving money. Now it feels obvious: the best model changes constantly. GPT, Claude, Gemini, Grok, Qwen, DeepSeek, Kimi, GLM - prices and capabilities move every week. So we’re opening up access to everyone. One OpenAI-compatible endpoint. The right model for every request. Lower cost without rewriting your app. Reserve access to use it.

English
19
5
72
18.4K
RaghuVaran
RaghuVaran@RaghuModupalli·
@Lentils80 So they don't have compute to release bigger models ?? Or they might be focusing Inference speend and costs for enterprise? Or they are little far ahead in terms of benchmarks and staying low for now ??
English
2
0
3
5.1K
Lentils
Lentils@Lentils80·
🚨 Breaking: Gemini 3.6 Flash, ID "gemini-3.6-flash-tiered", appeared in Antigravity a few minutes ago
Lentils tweet media
English
72
76
1K
257.2K
RaghuVaran
RaghuVaran@RaghuModupalli·
@GabbbarSingh Yes. Agreed and in crisis the information is worth thant he baits
English
0
0
0
340
Gabbar
Gabbar@GabbbarSingh·
I think as a nation if we ban any kind of social media monetisation by platforms. Be it YouTube, Instagram or Twitter. Don’t ban content. Just switch off monetisation. I feel a lot of problems will automatically get solved.
English
454
1.4K
10.8K
286.8K
RaghuVaran
RaghuVaran@RaghuModupalli·
@cb_doge Why should we even use excel in the forst place ??
English
0
2
3
55
DogeDesigner
DogeDesigner@cb_doge·
BREAKING: Grok 4.5 for Excel is now live. It works directly inside Excel to: • Analyze data • Write formulas in plain English • Create charts • Build financial models • Run forecasts and scenarios No exports or copied tables. Just Grok inside your workbook.
DogeDesigner tweet media
English
225
420
2.7K
112.6K
Ramsri Goutham Golla
Ramsri Goutham Golla@ramsri_goutham·
Popeye eats spinach because he hasn’t tasted thotakura!
Ramsri Goutham Golla tweet media
English
2
0
28
1.4K
RaghuVaran
RaghuVaran@RaghuModupalli·
OpenWiki 0.2 is officially adopting the Open Knowledge Format (OKF) spec. By adding standard YAML front matter to your docs, you can now unlock: ✅ Deterministic search and retrieval for AI agents ✅ Better organization with index.mmd and log.mmd ✅ Integration with the growing OKF open-source ecosystem Check out the repo and get started: #OpenWiki" target="_blank" rel="nofollow noopener">github.com/langchain-ai/o… #LangChain #OpenSource #OKF #KnowledgeManagement
English
0
0
3
33
RaghuVaran
RaghuVaran@RaghuModupalli·
@jerryjliu0 Hybrid search will always standout ad the best one
English
0
0
0
27
Jerry Liu
Jerry Liu@jerryjliu0·
We've built the following document retrieval endpoints into LlamaParse: * Hybrid search (grep + vector search) * File grep (grep incl. regex search) * File find (`find`) * File read (`sed`) We're continuing to experiment to see what combination allows agents to get the highest retrieval quality over unstructured docs. If you have thoughts let us know!
Jerry Liu tweet media
Jerry Liu@jerryjliu0

I'm glad people still understand the importance of building high-quality retrieval systems in 2026, especially as the outer models/harnesses are getting better every day. Making agentic retrieval work in production doesn't necessarily require groundbreaking new techniques around retrieval or planning. This article shows that you do need to spend engineering time tuning chunking, synchronization, reranking, tool API design, permissioning, and more. Some interesting tidbits: * Concatenating onto existing Slack threads as one contiguous chunk with heuristics for determining additional relevant context * Real-time updates for Slack * Separate chunking/updates for codebases * The discovery that hybrid search works well (not like this was a super new realization, but always good to validate and understand the specific parameters they tweaked) * Having natural guardrails on which data sources are relevant for which projects Building simple retrieval is easy, building production retrieval is hard. We had to deal with a lot of these challenges when productionizing our own Index feature within LlamaParse.

English
19
7
58
6.4K

Keşfet

@JensenHuang @nvidia @NVIDIA @jack @jain_harshit @dedene @OpenAI @huggingface