Sharath

Sharath

Nov 14

Systems Blueprint: ReA-Bench: Benchmarking Responsible Agent Auditing

#systems #architecture #infrastructure #performance

2 min read

Sharath

Nov 14

DIY Guide: Self-hosted Sentry: where the 16 GB actually goes (measured)

#diy #selfhosting #systems #opensource

2 min read

Sharath

Nov 14

Systems Blueprint: Can an AI Agent Be Epistemically Akratic? Higher-Order Evidence & the Limits of Self-Correction

#systems #architecture #infrastructure #performance

3 min read

Sharath

Nov 14

DIY Guide: From Subscriptions to Self-Hosting: Let an AI Agent Manage Your Home Server

#diy #selfhosting #systems #opensource

3 min read

Sharath

Nov 14

Tech & AI Synthesis: Experience-Handoff Reinforcement Learning for Recursive Self-Improvement

#ai #tech #deeplearning #multimodal

3 min read

Sharath

Nov 14

Market Intelligence: SEC Issues Exemptive Relief from Treasury Clearing Requirements for Certain Inter-Affiliate and Non-U.S. Repo Transactions

#finance #marketwatch #macro #valuation

3 min read

Sharath

Nov 13

Tech & AI Synthesis: Teaching a 135M-Parameter Model to Summarize with RLHF: SFT, Reward Modelling, PPO and DPO from…

#ai #tech #deeplearning #multimodal

3 min read

Sharath

Nov 13

Market Intelligence: Chicago Fed's Goolsbee says central bank 'has definitely got work to do' on inflation

#finance #marketwatch #macro #valuation

3 min read

Sharath

Nov 13

DIY Guide: G-STAR: Group-Scaled Token Capacity for Deeply Compressed Autoregressive Generation

#diy #selfhosting #systems #opensource

2 min read

Sharath

Nov 13

Tech & AI Synthesis: I Ran the Full RLHF Pipeline on a Free GPU, Then Pitted PPO Against DPO

#ai #tech #deeplearning #multimodal

3 min read

Sharath

Nov 13

Tech & AI Synthesis: GTAGym: Real AAA Game Tasks Environment for Evaluation and Reinforcement Learning

#ai #tech #deeplearning #multimodal

3 min read

Sharath

Nov 13

Market Intelligence: Alibaba announces plans to list T-Head, its Nvidia chip rival

#finance #marketwatch #macro #valuation

3 min read

Sharath

Nov 12

DIY Guide: Day 4: Optimizing Model Weights — Quantization Basics (GGUF, AWQ) for Efficient Inference

#diy #selfhosting #systems #opensource

2 min read

Sharath

Nov 12

Market Intelligence: In a policy switch, the Fed says its October 2027 meeting will not see a vote on interest rates

#finance #marketwatch #macro #valuation

3 min read

Sharath

Nov 12

DIY Guide: Is Netdata Worth Self-Hosting on a Home Server? 3-Year Cost of Netdata Open Source vs Netdata Cloud vs Datadog

#diy #selfhosting #systems #opensource

6 min read

Sharath

Nov 12

DIY Guide: Your Own Speech-to-Text Server: Faster Than Typing, Private by Default

#diy #selfhosting #systems #opensource

5 min read

Sharath

Nov 11

Systems Blueprint: Spikes vs Attention: Where Neuromorphic Chips Actually Save Energy

#systems #architecture #infrastructure #performance

5 min read

Sharath

Nov 10

Systems Blueprint: One Omni Model, Two GGUF Files: What LFM3-Omni-2B Really Costs in RAM, from the Tensor Headers Up

#systems #architecture #infrastructure #performance

6 min read

Sharath

Nov 10

DIY Guide: llm-compressor for vLLM: The FP8/AWQ Deployment Tradeoff

#diy #selfhosting #systems #opensource

5 min read

Sharath

Nov 9

DIY Guide: Self-Hosted Isn’t the Same as Owned, So I Built My Own Notes App

#diy #selfhosting #systems #opensource

2 min read

Sharath

Nov 9

DIY Guide: Complete Meeting Transcription at Home: faster-whisper + Ollama + Nomily (BYOD)

#diy #selfhosting #audio #whisper

3 min read

Sharath

Nov 8

Systems Blueprint: I Attacked a Real LLM Agent With Hidden Text. Here's What It Did (Free Kaggle Notebooks)

#systems #architecture #infrastructure #performance

2 min read

Sharath

Nov 8

DIY Guide: D3 Decision Models: Build Fast, Multimodal AI Applications Locally with vLLM

#diy #selfhosting #systems #opensource

2 min read

Sharath

Nov 7

Systems Blueprint: AI Is More Than LLMs: The 70-Year Story From Turing to Agent

#systems #architecture #infrastructure #performance

2 min read

Sharath

Nov 7

Systems Blueprint: Does Hindsight memory actually change agent behavior? I tested it

#systems #architecture #infrastructure #performance

2 min read

Sharath

Nov 6

Systems Blueprint: Building an AI for hard conversations: five agents, one safety regex, and a supervisor who graded us blind

#systems #architecture #infrastructure #performance

2 min read

Sharath

Nov 5

Tri-Hybrid Architecture Deep Dive: Liquid AI's LFM3-1.7B, Sub-Millisecond Convolutions, and 256K Context on Edge Silicon

#liquidai #lfm3 #architecture #edgeai

7 min read

Sharath

Nov 5

Research Synthesis: Inside the Architectures of Open-Source LLMs: Attention, MoE, Hybrid Layers and Quantization

#ai #research #deeplearning #knowledgegraphs

2 min read

Sharath

Nov 5

DIY Private AI Agent Gateway: Building a Resilient Semantic Router for Local Coding Models

#diy #selfhosting #agents #architecture

3 min read

Sharath

Nov 5

DIY Self-Hosting 35B+ Reasoning LLMs with NVFP4 Quantization and vLLM

#diy #selfhosting #vllm #nvfp4

1

3 min read

DEV Community

Badges

Writing Debut

Systems Blueprint: ReA-Bench: Benchmarking Responsible Agent Auditing

Want to connect with Sharath?

DIY Guide: Self-hosted Sentry: where the 16 GB actually goes (measured)

Systems Blueprint: Can an AI Agent Be Epistemically Akratic? Higher-Order Evidence & the Limits of Self-Correction

DIY Guide: From Subscriptions to Self-Hosting: Let an AI Agent Manage Your Home Server

Tech & AI Synthesis: Experience-Handoff Reinforcement Learning for Recursive Self-Improvement

Market Intelligence: SEC Issues Exemptive Relief from Treasury Clearing Requirements for Certain Inter-Affiliate and Non-U.S. Repo Transactions

Tech & AI Synthesis: Teaching a 135M-Parameter Model to Summarize with RLHF: SFT, Reward Modelling, PPO and DPO from…

Market Intelligence: Chicago Fed's Goolsbee says central bank 'has definitely got work to do' on inflation

DIY Guide: G-STAR: Group-Scaled Token Capacity for Deeply Compressed Autoregressive Generation

Tech & AI Synthesis: I Ran the Full RLHF Pipeline on a Free GPU, Then Pitted PPO Against DPO

Tech & AI Synthesis: GTAGym: Real AAA Game Tasks Environment for Evaluation and Reinforcement Learning

Market Intelligence: Alibaba announces plans to list T-Head, its Nvidia chip rival

DIY Guide: Day 4: Optimizing Model Weights — Quantization Basics (GGUF, AWQ) for Efficient Inference

Market Intelligence: In a policy switch, the Fed says its October 2027 meeting will not see a vote on interest rates

DIY Guide: Is Netdata Worth Self-Hosting on a Home Server? 3-Year Cost of Netdata Open Source vs Netdata Cloud vs Datadog

DIY Guide: Your Own Speech-to-Text Server: Faster Than Typing, Private by Default

Systems Blueprint: Spikes vs Attention: Where Neuromorphic Chips Actually Save Energy

Systems Blueprint: One Omni Model, Two GGUF Files: What LFM3-Omni-2B Really Costs in RAM, from the Tensor Headers Up

DIY Guide: llm-compressor for vLLM: The FP8/AWQ Deployment Tradeoff

DIY Guide: Self-Hosted Isn’t the Same as Owned, So I Built My Own Notes App

DIY Guide: Complete Meeting Transcription at Home: faster-whisper + Ollama + Nomily (BYOD)

Systems Blueprint: I Attacked a Real LLM Agent With Hidden Text. Here's What It Did (Free Kaggle Notebooks)

DIY Guide: D3 Decision Models: Build Fast, Multimodal AI Applications Locally with vLLM

Systems Blueprint: AI Is More Than LLMs: The 70-Year Story From Turing to Agent

Systems Blueprint: Does Hindsight memory actually change agent behavior? I tested it

Systems Blueprint: Building an AI for hard conversations: five agents, one safety regex, and a supervisor who graded us blind

Tri-Hybrid Architecture Deep Dive: Liquid AI's LFM3-1.7B, Sub-Millisecond Convolutions, and 256K Context on Edge Silicon

Research Synthesis: Inside the Architectures of Open-Source LLMs: Attention, MoE, Hybrid Layers and Quantization

DIY Private AI Agent Gateway: Building a Resilient Semantic Router for Local Coding Models

DIY Self-Hosting 35B+ Reasoning LLMs with NVFP4 Quantization and vLLM