iryna_kondr
Ask HN: What are your strategies for reviewing AI generated code?
Almost everyone I talk to feels the pain of reviewing code generated with LLMs. It feels like humans have become the bottleneck in the development process.Some teams are setting guardrails, like limiting PR size or enforcing a max number of changed lines, but it still feels like everyone is figuring this out in real time.What has actually worked for you to make reviewing AI generated code easier?
Show HN: Self-improving skills for any coding agent
Re:Dreamer: Make any coding agent self-evolving, across the whole team
on Tuesday May 05, 2026 @01:56PM (#48026092)
Thanks for the feedback!
Dreamer: Make any coding agent self-evolving, across the whole team
Re:Dreamer: Make any coding agent self-evolving, across the whole team
on Tuesday May 05, 2026 @01:33PM (#48025775)
Dreamer is a framework inspired by Claude's dream mode, but extends it to any Coding CLI and multiple users at the same time.
In short, agents submit short memories through an MCP server when they hit something the current context didn't cover. Then, a scheduled "dream" consolidates each batch into long-term memory and updates the AGENTS.md and skills from it. The produced skills can be pushed to git and fed back to the agents, essentially enabling the autonomous self-evolution loop
Main features:
- Works with any coding agent that supports MCP and skills.
- Works across the team: submissions pool across everyone's sessions and aggregated into a team-level context.
- Output is plain AGENTS.md plus skills, so it is easy to version, review, edit.
- Extensible by design. Every component (short term memory, long term memory, dreamer model, hooks, etc) is a Python Protocol and is wired from a runtime config, so virtually anything can be swapped/extended.
Github repo: https://github.com/luml-ai/dreamer
Blogpost: https://luml.ai/blog/2026/dreamer-self-evolving-agents
Re:AI fatigue is real and nobody talks about it
on Sunday February 08, 2026 @10:26AM (#46935074)
I’ve definitely been feeling that shift too. What have you guys found that helps with this? Any habits you use to avoid the constant context switching and decision fatigue?
Re:Show HN: Minikv – Distributed key-value and object store in Rust (R...
on Tuesday February 03, 2026 @08:26AM (#46870692)
Hi Emilie, nice project, thanks for sharing. I’m curious whether there were any decisions that you added mainly for educational value even though you wouldn’t make the same call in a production system?
Show HN: AGENTS.lock – a package manager for Agents/Skills/MCPs
https://github.com/luml-ai/AGENTS.lock
AGENTS.lock keeps AI agent skills, instructions, and MCP servers in sync across Claude, Codex, Gemini, and Copilot CLIs using a single TOML lockfile as the source of truth.Instead of manually copying skills and configs between tools, you declare everything once in AGENTS.lock and run `al sync`.GitHub: https://github.com/luml-ai/AGENTS.lock
Re:There Is an AI Code Review Bubble
on Tuesday January 27, 2026 @04:03AM (#46777352)
My experience is similar. AI's context is limited to the codebase. It has limited or no understanding of the broader architecture or business constraints, which adds to the noise and makes it harder to surface the issues that actually matter.
Re:Show HN: Quantum Tunnel
on Monday January 05, 2026 @04:16AM (#46496767)
Great visualization! What part of this project was the hardest to get “right” (math, overall aesthetic balance, etc.)?
Show HN: Dingo: Rapid Prototyping of RAG-Powered Applications
Show HN: Scikit-LLM seamlessly integrate LLMs into scikit-learn
https://github.com/iryna-kondr/scikit-llm
Scikit-LLM is an open-source library that allows to seamlessly integrate powerful language models like ChatGPT into scikit-learn for enhanced text analysis tasks.
Show HN: Agent Dingo – a microframework for buildling conversational AI agents
https://github.com/BeastByteAI/agent_dingo
AgentDingo allows you to register the functions to use with ChatGPT. It is possible to convert Langchain Tools into function descriptors in order to register them with Dingo. The intermediate function calling is also handled by the agent directly. Once the functions are registered, you can run the conversation using the chat method of the agent, or serve the agent on a web server (also...