Hyperagents · HackerPapers discussions

Hyperagents — HN submission

Sat, 23 May 2026 14:02:30 GMT

Hyperagents (Meta Research)

2 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Hyperagents — HN submission

Wed, 01 Apr 2026 04:45:06 GMT

Show HN: Calx – track and compile corrections humans make with AI agents

Last year I got laid off and started building a company. Fast forward to a month ago, I built a production system with 6 AI agents across 82,000 lines of code in 20 days for $250. I kept obsessive correction logs. Every time an agent made a mistake and I told it what to do differently, and I made sure it logged the correction itself. When I transferred 237 of those corrections as rules to a new agent to save time with onboarding in a new repo, it made 44 new mistakes. 13 were in categories the rules explicitly covered. The rules were present in context. The behavior wasn't there. I published…

3 points; 1 discussion reply on HN. Paper and source history. A submission is not an endorsement.

Hyperagents — mentioned by NitpickLawyer

Thu, 26 Mar 2026 18:08:02 GMT

The paper is here - https://arxiv.org/pdf/2603.19461 This, IMO is the biggest insight into where we're at and where we're going: > Because both evaluation and self-modification are coding tasks, gains in coding ability can translate into gains in self-improvement ability. There's a thing that I've noticed early into LLMs: once they unlock one capability, you can use that capability to compose stuff and improve on other, related or not, capabilities. For example "reflexion" goes into coding - hey, this didn't work, let me try ... Then "tools". Then "reflxion" + "tools". And so on. You can get…

Paper and discussion history. A mention is not an endorsement.

Hyperagents — mentioned by pegasus

Thu, 26 Mar 2026 17:50:28 GMT

There's a paper at https://arxiv.org/abs/2603.19461 Abstract: Self-improving AI systems aim to reduce reliance on human engineering by learning to improve their own learning and problem-solving processes. Existing approaches to self-improvement rely on fixed, handcrafted meta-level mechanisms, fundamentally limiting how fast such systems can improve. The Darwin Gödel Machine (DGM) demonstrates open-ended self-improvement in coding by repeatedly generating and evaluating self-modified variants. Because both evaluation and self-modification are coding tasks, gains in coding ability can…

Paper and discussion history. A mention is not an endorsement.

Hyperagents — HN submission

Tue, 24 Mar 2026 16:54:10 GMT

HyperAgents: Self-referential self-improving agents

https://arxiv.org/abs/2603.19461

234 points; 90 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Hyperagents — HN submission

Tue, 24 Mar 2026 15:07:47 GMT

Hyperagents

3 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Hyperagents — HN submission

Mon, 23 Mar 2026 16:28:29 GMT

Hyperagents

3 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.