Forem

Oleg Klimov profile picture

Oleg Klimov

Founder of Refact.ai, Open-Source AI Agent for IDE | ex-OpenAI

Location UK Joined Joined on  Personal website https://refact.ai

Work

CEO at Refact.ai

How we built the open-source SOTA AI Agent on SWE-bench Verified
refactai_olegklimov profile

How we built the open-source SOTA AI Agent on SWE-bench Verified

#programming #ai #machinelearning #computerscience
Comments
9 min read

Want to connect with Oleg Klimov?

Create an account to connect with Oleg Klimov. You can also sign in below to proceed if you already have an account.

Create Account
Already have an account? Sign in
#1 on SWE-bench lite, achieved fully autonomously by open-source Refact.ai Agent
refactai_olegklimov profile

#1 on SWE-bench lite, achieved fully autonomously by open-source Refact.ai Agent

#programming #ai #llm #opensource
Comments
6 min read
#1 on SWE-bench Lite, achieved fully autonomously by open-source Refact.ai Agent
refactai_olegklimov profile

#1 on SWE-bench Lite, achieved fully autonomously by open-source Refact.ai Agent

#programming #ai #opensource #machinelearning
Comments
6 min read
Top-10 Tips for Conscious Vibe Coding
refactai_olegklimov profile

Top-10 Tips for Conscious Vibe Coding

#programming #ai
8
Comments
8 min read
Refact.ai Agent scores highest on Aider's Polyglot Benchmark: 93.3% with Thinking Mode, 92.9% without
refactai_olegklimov profile

Refact.ai Agent scores highest on Aider's Polyglot Benchmark: 93.3% with Thinking Mode, 92.9% without

#ai #programming #machinelearning
11
Comments 1
6 min read
Our AI Agent + 3.7 Sonnet ranked #1 on Aider’s polyglot bench — a 76.4% score
refactai_olegklimov profile

Our AI Agent + 3.7 Sonnet ranked #1 on Aider’s polyglot bench — a 76.4% score

#programming #ai #chatgpt #llm
11
Comments
4 min read
Refact.ai AI Agent is the new #1 on Aider’s polyglot benchmark with a score of 76.4%(a better measure than SWE bench?)
refactai_olegklimov profile

Refact.ai AI Agent is the new #1 on Aider’s polyglot benchmark with a score of 76.4%(a better measure than SWE bench?)

#ai #llm #githubcopilot #coding
1
Comments
4 min read
Developing AI Agent: SWE bench critics, speed-smart trade-off, and how to make the agent useful
refactai_olegklimov profile

Developing AI Agent: SWE bench critics, speed-smart trade-off, and how to make the agent useful

#ai #machinelearning #deeplearning
2
Comments
6 min read
Programming with AI: Autonomous Agents vs. Our Dream
refactai_olegklimov profile

Programming with AI: Autonomous Agents vs. Our Dream

#ai #machinelearning #productivity #deeplearning
1
Comments
6 min read
Introducing Refact.ai: The Customizable AI Coding Assistant
refactai_olegklimov profile

Introducing Refact.ai: The Customizable AI Coding Assistant

#ai #aicodingassistant
Comments
1 min read
Implementing RAG in Refact.ai AI Coding Assistant
refactai_olegklimov profile

Implementing RAG in Refact.ai AI Coding Assistant

#rag #opensource #development
12
Comments
8 min read
loading...
OSZAR »