Top all-time · #3644
Imbue
Company blog · imbue.com/blogaiprogramming
Imbue is the company blog at imbue.com, writing about ai and programming. Since 2023, 21 different Hacker News readers have linked it 74 times, most often “Usefully run 100s of Claudes in parallel with mngr”. No feed was found, so read it on the site itself.
Too few sampled comments (14) to say how often HN recommends it.?
Why HN links it
HN readers link Imbue's site mostly for product pages such as Sculptor and mngr, and for research posts on AI coding agents and training a 70B model from bare metal.
Summarised by Claude from a sample of 14 HN comments that link here. Each comment is marked recommending, critical or neutral (citing without judging); how this works.
We build AI to help people think, create, and build. Tools that are loyal to you, not the company that built them.
Most-linked posts?
- Usefully run 100s of Claudes in parallel with mngr3 people · 4 mentions · first linked 2026-04-02
- Training a 70B Model from Scratch3 people · 3 mentions · first linked 2024-06-25
- Infrastructure setup and open-source scripts to train 70B model from bare metal3 people · 3 mentions · first linked 2024-06-25
- /sculptor2 people · 3 mentions · first linked 2025-10-08
- Show HN: Sculptor – A UI for Claude Code2 people · 3 mentions · first linked 2025-09-30
- LLM-Based Evolution as a Universal Optimizer2 people · 2 mentions · first linked 2026-02-27
- How Offload Works: Inside the Rust CLI that sped up our tests by 6x2 people · 2 mentions · first linked 2026-04-07
What Hacker News says?
The project itself is open source and doesn't have any AI features. Also while Imbue is in some sense an AI startup it does have a very different ethos from a lot of tech companies: https://imbue.com/about
Comment linking /about
on “Cloud in a Bottle: making self-hosting accessible to everyone”Submitted Infrastructure setup and open-source scripts to train 70B model from bare metal as a story · 325 points
HN discussionI resonate on the exhaustion — actually, the context switching fatigue is why we built Sculptor for ourselves ( https://imbue.com/sculptor ). We usually see devs running 4-6 agents in parallel today using Sculptor today. Personally I think much of the fatigue comes from: 1) friction in spawning agents 2) friction in reviewing agent changes 3) context management annoyance when e.g. you start debugging part of the age…
Comment linking /sculptor
on “Vibe engineering”Submitted Show HN: Sculptor – A UI for Claude Code as a story · 176 points
HN discussionSince Sculptor allows you to use custom docker containers (devcontainers), you can check out the other projects in there. Then your primary project (from Sculptor's perspective) is simply whatever contains the devcontainer / dockerfile that you want it to use (to pull in all of those repos) It's still a little awkward though -- if you do this, be sure to set a custom system prompt explaining this setup to the underl…
Comment linking /sculptor/
on “Vibe engineering”Submitted Sculptor: Catch and fix issues as you code as a story · 61 points
HN discussionHey, Kanjun from Imbue here! This is exactly why we built Sculptor ( https://imbue.com/sculptor ), a desktop UI for Claude Code. Each agent has its own isolated container. With Pairing Mode, you can sync the agent's code and git state directly into your local Cursor/any IDE so you can instantly validate its work. The sync is bidirectional so your local changes flow back to the agent in realtime. Happy to answer any…
Comment linking /sculptor
on “Claude Code on the web”Submitted Show HN: Vet – Prevent coding agents from making mistakes as a story · 14 points
HN discussionImbue | Machine Learning Engineer | Remote or San Francisco | Full-time Imbue builds AI systems that reason and code, enabling AI agents to accomplish larger goals and safely work in the real world. We train our own foundation models optimized for reasoning and prototype agents on top of these models. By using these agents extensively, we gain insights into improving both the capabilities of the underlying models an…
Comment linking /careers
on “Ask HN: Who is hiring? (May 2024)”Submitted Show HN: Control your X/Twitter feed using a small on-device LLM as a story · 13 points
HN discussionImbue | Engineering Manager | San Francisco | Full-time Imbue builds AI systems that reason and code, enabling AI agents to accomplish larger goals and safely work in the real world. We train our own foundation models optimized for reasoning and prototype agents on top of these models. By using these agents extensively, we gain insights into improving both the capabilities of the underlying models and the interactio…
Comment linking /careers
on “Ask HN: Who is hiring? (July 2024)”Submitted Tripling an LLM's ARC-AGI-2 score with code evolution as a story · 12 points
HN discussionImbue | Founding Product Engineers | San Francisco (ONSITE) | Full-time Imbue builds AI systems that reason and code, enabling AI agents to accomplish larger goals and safely work in the real world. We train our own foundation models optimized for reasoning and prototype agents on top of these models. By using these agents extensively, we gain insights into improving both the capabilities of the underlying models an…
Comment linking /careers
on “Ask HN: Who is hiring? (February 2025)”Submitted Usefully run 100s of Claudes in parallel with mngr as a story · 10 points
HN discussionImbue | Machine Learning Engineer | Remote or San Francisco | Full-time Imbue builds AI systems that reason and code, enabling AI agents to accomplish larger goals and safely work in the real world. We train our own foundation models optimized for reasoning and prototype agents on top of these models. By using these agents extensively, we gain insights into improving both the capabilities of the underlying models an…
Comment linking /careers
on “Ask HN: Who is hiring? (September 2024)”Submitted Training a 70B Model from Scratch as a story · 10 points
HN discussionImbue | Senior Software Engineer | Remote or San Francisco | Full-time Imbue builds AI systems that reason and code, enabling AI agents to accomplish larger goals and safely work in the real world. We train our own foundation models optimized for reasoning and prototype agents on top of these models. By using these agents extensively, we gain insights into improving both the capabilities of the underlying models and…
Comment linking /careers
on “Ask HN: Who is hiring? (February 2024)”Submitted How Offload Works: Inside the Rust CLI that sped up our tests by 6x as a story · 9 points
HN discussionImbue | Machine Learning Engineer | Remote or San Francisco | Full-time Imbue builds AI systems that reason and code, enabling AI agents to accomplish larger goals and safely work in the real world. We train our own foundation models optimized for reasoning and prototype agents on top of these models. By using these agents extensively, we gain insights into improving both the capabilities of the underlying models an…
Comment linking /careers
on “Ask HN: Who is hiring? (January 2024)”Submitted Offload: Speed up the agent loop by running tests remotely as a story · 8 points
HN discussionImbue | Engineering Manager | San Francisco | Full-time Imbue builds AI systems that reason and code, enabling AI agents to accomplish larger goals and safely work in the real world. We train our own foundation models optimized for reasoning and prototype agents on top of these models. By using these agents extensively, we gain insights into improving both the capabilities of the underlying models and the interactio…
Comment linking /careers
on “Ask HN: Who is hiring? (June 2024)”Submitted From bare metal to a 70B model: infrastructure set-up and scripts as a story · 7 points
HN discussionImbue | Machine Learning Engineer | Remote or San Francisco | Full-time Imbue builds AI systems that reason and code, enabling AI agents to accomplish larger goals and safely work in the real world. We train our own foundation models optimized for reasoning and prototype agents on top of these models. By using these agents extensively, we gain insights into improving both the capabilities of the underlying models an…
Comment linking /careers
on “Ask HN: Who is hiring? (August 2024)”Submitted We used Gemma to detect AI text locally on iPhone as a story · 6 points
HN discussionImbue | Engineering Manager | San Francisco | Full-time Imbue builds AI systems that reason and code, enabling AI agents to accomplish larger goals and safely work in the real world. We train our own foundation models optimized for reasoning and prototype agents on top of these models. By using these agents extensively, we gain insights into improving both the capabilities of the underlying models and the interactio…
Comment linking /careers
on “Ask HN: Who is hiring? (April 2024)”Submitted Imbue Studio: the future of personal computing as a story · 4 points
HN discussionImbue [ https://imbue.com ] | Infrastructure Engineers | San Francisco (ONSITE) | Full-time Imbue is building a coding agent environment ( https://imbue.com/product/sculptor/ ) that imbues engineering wisdom into LLM workflows—so anyone has the power to create software they can trust. We aim to rekindle the dream of personal computing and make software creation accessible to all, so every person can have the power t…
Comment linking /careers
on “Ask HN: Who is hiring? (June 2025)”Submitted Using evolution to automate AI model research as a story · 4 points
HN discussionImbue | Senior Software Engineer | Remote or San Francisco | Full-time Imbue builds AI systems that reason and code, enabling AI agents to accomplish larger goals and safely work in the real world. We train our own foundation models optimized for reasoning and prototype agents on top of these models. By using these agents extensively, we gain insights into improving both the capabilities of the underlying models and…
Comment linking /careers
on “Ask HN: Who is hiring? (March 2024)”Submitted Use plain old REST instead of MCP as a story · 4 points
HN discussion
