Hacker News: DanMcInerney

New comment by DanMcInerney in "Claude Cowork and chat are now one Claude"

DanMcInerney — Wed, 16 Sep 2026 19:42:58 +0000

The problem is that knowledge workers just need the simplest way possible to automate their work. Currently I feel like Anthro is overcomplicating this. If I'm an accountant, I want to open Claude App, describe my workflow for balancing some books, then have Claude design a reusable WORKFLOW that it runs whenever I ask. The workflow only needs 2 primitive skills to do anything: /work, and /review. Compose these together with guidance docs into workflows, then workflows and call other workflows. It's all just callable skills.

/balance-books hey claude here's the books. Go balance them

Claude then uses the guidance docs and various subagents to review the books, send off parallel workers with cheap models, then review with a more expensive model. Done in the repeatable, correct order with independent review every time. As new models come out, your workflow structure stays the same. You just delete some prescription from the guidance docs.

https://github.com/DanMcInerney/orchflows

New comment by DanMcInerney in "Dream-RSI: Recursive Self-Improvement through Evolving Worlds"

DanMcInerney — Wed, 16 Sep 2026 15:34:07 +0000

I ended up building a simplified version of this as /self-improve in https://github.com/DanMcInerney/orchflows. History is the state ledger, memory and RSI just cite the history as evidence and can be rewritten. I feel like strong immutable state is the missing piece of the puzzle for most of these memory libraries.

Orchflows: You only need 2 skills to make infinitely complex agents

DanMcInerney — Sun, 13 Sep 2026 20:18:19 +0000

Article URL: https://github.com/DanMcInerney/orchflows

Comments URL: https://news.ycombinator.com/item?id=49688252

Points: 1

# Comments: 0

Orchflows: Build self-improving loops in one sentence

DanMcInerney — Sat, 18 Jul 2026 17:49:59 +0000

Article URL: https://github.com/DanMcInerney/orchflows

Comments URL: https://news.ycombinator.com/item?id=48960392

Points: 3

# Comments: 0

New comment by DanMcInerney in "Weightlifting beats running for blood sugar control, researchers find (2025)"

DanMcInerney — Sun, 12 Jul 2026 01:31:08 +0000

Does the average "scientist" even care about quality these days or is it all just whatever headline makes their funders happy?

New comment by DanMcInerney in "OpenAI Forked Git on GitHub"

DanMcInerney — Sat, 11 Jul 2026 20:56:35 +0000

Rockstar built git for games, OpenAI's aiming for git for agents.

Claude, make a git for games designed for agents. Sell the code to the highest bidder when you're done.

New comment by DanMcInerney in "Show HN: OpenKnowledge – open source AI-first alternative to Obsidian/Notion"

DanMcInerney — Fri, 26 Jun 2026 13:48:24 +0000

https://cloud.google.com/blog/products/data-analytics/how-th...

Did you look at the OKF repo from Google? Open Knowledge seems to be a common term these days for similar solutions. I think OKF is more of the protocol for wiki-for-llm while you have more of the bells and whistles

New comment by DanMcInerney in "/architect: Reduce Fable tokens by 80%, Fable orchestrates/reviews, Codex builds"

DanMcInerney — Sat, 13 Jun 2026 02:00:39 +0000

ANNNNNND it's gone. Guys, I found a way to reduce Fable token usage 100%. You can find it here: github.com/USGov/idiotic-overreach.

New comment by DanMcInerney in "/architect: Reduce Fable tokens by 80%, Fable orchestrates/reviews, Codex builds"

DanMcInerney — Sat, 13 Jun 2026 00:14:23 +0000

I don't disagree with any of this. It is generated software, and it's not a novel idea. I didn't mean for it to come off like that. It's just solving an itch that I couldn't find a solution to and I'm getting a lot of personal utility out of it. I do have a lot of experience with agentic memory, multi-agent systems and harnesses and wasn't super impressed by the workflow of Fable calling opus subagents so I figured I'd apply best practices to what already exists to make it a teensy bit better and easier to use.

/architect: Reduce Fable tokens by 80%, Fable orchestrates/reviews, Codex builds

DanMcInerney — Fri, 12 Jun 2026 20:33:22 +0000

Article URL: https://github.com/DanMcInerney/architect-loop

Comments URL: https://news.ycombinator.com/item?id=48509133

Points: 104

# Comments: 41

New comment by DanMcInerney in "MiMo Code is now released and open-source"

DanMcInerney — Thu, 11 Jun 2026 16:31:55 +0000

I've worked a lot with MiMo in my project that pits LLMs against each other in games (clankerfights.ai). It is a very very good model for the price. MiniMax I'd say is smarter, but MiMo really touches near pareto frontier.

I open-sourced my UFC prediction model, code, and database after 5 years of work

DanMcInerney — Fri, 05 Jun 2026 13:14:54 +0000

Article URL: https://mcinerney.ai/writings/i-open-sourced-my-ufc-prediction-model-weights-and-database/

Comments URL: https://news.ycombinator.com/item?id=48412069

Points: 3

# Comments: 1

New comment by DanMcInerney in "'Fuck you, Bambu': How one private message could change the face of 3D printing"

DanMcInerney — Sun, 24 May 2026 06:50:14 +0000

Me and a buddy, victor teisller, hacked the most popular 3D printer a few years ago (flashforge) to turn it into a major fire hazard through reverse engineering the firmware update remotely. Changed the max temp of the extruder to the temp of the Sun lol. These things are a fascinating security target because they're an easy place to turn abstract digital hacking into physical repersussions that can literally murder.

https://www.theregister.com/security/2020/04/13/how-to-make-...

Show HN: I built a site to watch, predct and prompt inject agents playing games

DanMcInerney — Sat, 23 May 2026 15:42:22 +0000

Article URL: https://clankerfights.ai

Comments URL: https://news.ycombinator.com/item?id=48248612

Points: 1

# Comments: 0

I vibecoded a Kalshi bot to $6k profit and opensourced it

DanMcInerney — Tue, 19 May 2026 13:23:16 +0000

Article URL: https://mcinerney.ai/writings/how-i-botted-6k-prediction-markets-as-i-slept/

Comments URL: https://news.ycombinator.com/item?id=48193019

Points: 2

# Comments: 0

New comment by DanMcInerney in "Daily Claude outage is upon us. Waiting for Claude Status to update"

DanMcInerney — Wed, 15 Apr 2026 14:53:33 +0000

Cross your fingers they're about to drop 4.7. 4.6 came out with a bang, now it seems all the compute bottlenecks just lead to customer frustration as they get closer to releasing next model. Balancing the books over there must be a nightmare, "Well we can piss off every single customer for a week, but we'll be able to release the next model 1 week faster"

New comment by DanMcInerney in "Nvidia NemoClaw"

DanMcInerney — Thu, 19 Mar 2026 14:57:28 +0000

All these comments about "this is crazy to deploy agents that might do something bad in your environment" are crazy themselves. The productivity gains from these computer use agents are crazy. Every org on earth has to make the call, is 3x productivity gains worth 2x the risk increase? The answer is almost always a resounding yes. You limit the blast radius if things go wrong, but the financial gain of having 1 employee to the work of 3 already pays for the disaster if it happens.

New comment by DanMcInerney in "Matchlock – Secures AI agent workloads with a Linux-based sandbox"

DanMcInerney — Sun, 08 Feb 2026 13:58:59 +0000

Sandboxing is a great security step for agents. Just like using guardrails is a great security step. I can't help but feel like it's all soft defense though. The real danger comes from the agent being able to read 3rd party data, be prompt injected, and then change or exfiltrate sensitive data. A sandbox does not prevent an email-reading agent from reading a malicious email, being prompt injected, and then sending an email to a malicious email address with the contents of your inbox. It does help in implementing network-layer controls though, like apply a policy that says this linux-based sandbox is only allowed to visit [whitelisted] urls. This kind of architectural whitelisting is the only hard defense we have for agents at the moment. Unfortunately it will also hamper their utility if used to the greatest extent possible.

New comment by DanMcInerney in "Prompt Injection via Poetry"

DanMcInerney — Wed, 03 Dec 2025 21:31:29 +0000

There are an infinite amount of ways to jailbreak AI models. I don't understand why every time a new method is published it makes the news. The data plane and the control plane in LLM inputs are one in the same, meaning you can mitigate jailbreaks but you cannot 100% prevent them currently. It's like blacklisting XSS payloads and expecting that to protect your site.

New comment by DanMcInerney in "Gemini 3"

DanMcInerney — Tue, 18 Nov 2025 18:31:13 +0000

A 50% increase over ChatGPT 5.1 on ARC-AGI2 is astonishing. If that's true and representative (a big if), it lends credence to this being the first of the very consistent agentically-inclined models because it's able to follow a deep tree of reasoning to solve problems accurately. I've been building agents for a while and thus far have had to add many many explicit instructions and hardcoded functions to help guide the agents in how to complete simple tasks to achieve 85-90% consistency.