Hacker News: ilusion

New comment by ilusion in "Ask HN: What Are You Working On? (July 2026)"

ilusion — Mon, 13 Jul 2026 05:49:08 +0000

I'm working on https://artifacts.iofold.com, a way to use artifacts (self contained html + optional assets like image/video/json) easily across agents, with feedback loop and docsend style wttribiti gates.

Have made it agent friendly enough that my teammates' agents can read and drop commennts on specs/storyboards etc, and my agent can close the loop by iterating with a new artifact version.

New comment by ilusion in "Show HN: RLM-based local debugger for AI agent traces"

ilusion — Wed, 24 Jun 2026 03:59:56 +0000

I'm very curious to see a benchmark for this - have toyed with the idea myself but haven't put in the hard work to test these hypothesis on extracting learning signal from deep-agent traces.

New comment by ilusion in "Show HN: Bhatti – Self-hostable Firecracker orchestrator with auto pause/wake"

ilusion — Sun, 03 May 2026 17:19:46 +0000

Excited to see this launch, have been using bhatti for some time now!

New comment by ilusion in "Agents that remember: introducing Cloudflare Agent Memory"

ilusion — Fri, 17 Apr 2026 20:01:40 +0000

The profile as a memory primitive is pretty interesting, how do you scale it for a scoped access/hierarchical setting? (for example, overall memory of processes => customer specific => project specific memory)

New comment by ilusion in "A 54KB client-side HNSW vector search engine in WASM"

ilusion — Fri, 27 Mar 2026 05:03:16 +0000

This is insane and obvious at the same time - why is everyone not doing this instead of server side retrieval for webrtc based voice agents?

New comment by ilusion in "Tell HN: Litellm 1.82.7 and 1.82.8 on PyPI are compromised"

ilusion — Tue, 24 Mar 2026 20:03:15 +0000

Does this mean opencode (and other such agent harnesses that auto update) might also be compromised?

New comment by ilusion in "Ask HN: What are you working on? (October 2025)"

ilusion — Mon, 13 Oct 2025 04:20:19 +0000

I've struggled with adding evals to my AI agents for last few months, and felt that vibe evals should have a path to building a robust system down the line.

Working on a plugin for langfuse to create evals functions and dataset from ingested traces automatically, based on ad-hoc user feedback.

New comment by ilusion in "Statement on Potentially Unlawful Online Platforms for Trading Digital Assets"

ilusion — Thu, 08 Mar 2018 08:12:00 +0000

bitcoin just needs to achieve a closed loop economy, and this won't sound as bad