Hacker News: schmuhblaster

"Prolog Swarms" – Beam-Like Concurrency in DeepClause

schmuhblaster — Thu, 15 Oct 2026 16:03:20 +0000

Article URL: https://deepclause.substack.com/p/prolog-swarms-beam-like-concurrency

Comments URL: https://news.ycombinator.com/item?id=50105636

Points: 1

# Comments: 0

A Harness in a single file: Agent skills as an evolving REPL module

schmuhblaster — Fri, 09 Oct 2026 15:45:17 +0000

Article URL: https://deepclause.substack.com/p/a-harness-in-a-single-file-agent

Comments URL: https://news.ycombinator.com/item?id=50022208

Points: 1

# Comments: 0

Jev, Prolog, Pi, and the dream of probabilistic logic programming

schmuhblaster — Mon, 21 Sep 2026 00:42:20 +0000

Article URL: https://deepclause.substack.com/p/jev-prolog-pi-and-the-dream-of-probabilistic

Comments URL: https://news.ycombinator.com/item?id=49781694

Points: 25

# Comments: 0

Running Doom on Linux inside TinyEmu inside Docker inside WASM inside Electron

schmuhblaster — Fri, 18 Sep 2026 07:15:56 +0000

Article URL: https://deepclause.substack.com/p/running-doom-on-risk-v-linux-inside

Comments URL: https://news.ycombinator.com/item?id=49751105

Points: 1

# Comments: 0

Show HN: Pi-box: Pi coding agent running inside a VM inside WASM inside Electron

schmuhblaster — Tue, 15 Sep 2026 00:21:19 +0000

Project background and human written summary here: https://deepclause.substack.com/p/pie-in-a-box-running-pi-on...

Comments URL: https://news.ycombinator.com/item?id=49706083

Points: 3

# Comments: 0

Pi(e) in a box: running pi on risk-v inside a VM inside TinyEmu inside WASM

schmuhblaster — Mon, 14 Sep 2026 04:45:06 +0000

Article URL: https://deepclause.substack.com/p/pie-in-a-box-running-pi-on-risk-v

Comments URL: https://news.ycombinator.com/item?id=49692094

Points: 2

# Comments: 0

New comment by schmuhblaster in "Procedural Graphs: Self-Evolving Execution Structures for LLM Agents"

schmuhblaster — Thu, 10 Sep 2026 01:23:49 +0000

Maybe I missed in when scanning the paper, but did they compare to a simple self modifying harness, e.g. instructing Pi to update some code or skill docs based on the results?

New comment by schmuhblaster in "Make SOPs executable: policies as deterministic logic programs with agent leaves"

schmuhblaster — Mon, 07 Sep 2026 12:51:17 +0000

Turning 100+ page SOP documents into executable policies using DeepClause and DML.

Building on the self-modifying harness concept we show here how to use DeepClause to build more reliable agents for outsourcing work defined via SOPs and policies. Instead of taking a big markdown file and putting it into the system prompt, we let a coding agent convert policies into small executable logic programs in a DSL called “DML”. The “leaves” of these programs can either be deterministic rules or LLM-driven agent loops. DML programs run safely inside the WASM build of SWI-Prolog.

Make SOPs executable: policies as deterministic logic programs with agent leaves

schmuhblaster — Mon, 07 Sep 2026 12:51:17 +0000

Article URL: https://deepclause.substack.com/p/make-sops-executable-policies-as

Comments URL: https://news.ycombinator.com/item?id=49597797

Points: 1

# Comments: 1

The Emergent Symbolic Structure of Artificial Neural Networks

schmuhblaster — Wed, 02 Sep 2026 04:15:56 +0000

Article URL: https://arxiv.org/abs/2608.29530

Comments URL: https://news.ycombinator.com/item?id=49531651

Points: 297

# Comments: 110

New comment by schmuhblaster in "I accidentally turned LLM memory into program analysis"

schmuhblaster — Sat, 29 Aug 2026 07:25:26 +0000

Great work! If anyone is looking for a way to integrate something like this into their own harness or the pi coding agent, then you might be interested in DeepClause [0]. It comes with a Prolog-like language implemented on top of SWI-Prolog (WASM Version). The purpose of the project is to allow for broad experimentation around the intersection of LLMs/Agents and GOFAI. So you could use it to build memory systems like OP did, create executable specs, define graphs and loops for agents and subagents... It also comes with a pi extension that greatly simplifies getting started with it.

Opposed to OP, DeepClause uses Prolog semantics, so running some more complex queries on knowledgebases might cause some issues (which is the use case where a Datalog might be more useful). For smaller scales it should be fine though.

[0] https://github.com/deepclause/deepclause-sdk [1] https://github.com/deepclause/deepclause-pi

New comment by schmuhblaster in "AWS Acquires DuckDB"

schmuhblaster — Wed, 26 Aug 2026 13:20:06 +0000

I've been super impressed by DuckDB ever since first trying it out about 3 three years ago. Congrats to the founders!

DeepClause meets pi: controlling pi with Prolog and vice versa

schmuhblaster — Fri, 21 Aug 2026 03:08:37 +0000

Article URL: https://deepclause.substack.com/p/deepclause-meets-pi-controlling-pi

Comments URL: https://news.ycombinator.com/item?id=49383277

Points: 2

# Comments: 0

New comment by schmuhblaster in "GLM-5.3: Frontier coding with emergent cyber capabilities"

schmuhblaster — Fri, 14 Aug 2026 13:47:48 +0000

I think that writing your own harness is a rite of passage now, just like writing your own search engine or database, rolling your own crypto…

Anyways, please try mine!

https://github.com/deepclause/deepclause-sdk

New comment by schmuhblaster in "Ask HN: What are you working on? (August 2026)"

schmuhblaster — Mon, 10 Aug 2026 16:56:25 +0000

That should be possible. You can e.g. take a look at the deep research example skill.

The Prolog/DML lets you express any kind of loop, graph, whatever workflow.

New comment by schmuhblaster in "Ask HN: What are you working on? (August 2026)"

schmuhblaster — Mon, 10 Aug 2026 14:16:24 +0000

I’ve been working on DeepClause [0], an agentic harness, the core of which is based on Prolog. Every interaction (conversation turn, plan, execute plan, etc.) triggers a small logic program that orchestrates one or more agent loops or prompts. All these programs are completely hackable, so you can easily adjust the core logic and behavior of your agents in a reliable manner. Also, instead of using markdown specs, you can “compile” your markdown into Prolog code. My hope is that this might unlock new possibilities for spec driven development.

It’s been a lot of fun and I am somewhat proud of Prolog/Typescript integration layer built on SWI Prolog’s WASM version.

Other than that, I am not sure how and if I will continue with it. Feedback welcome!

[0] https://github.com/deepclause/deepclause-sdk

New comment by schmuhblaster in "Is AI reasoning right for the wrong reasons?"

schmuhblaster — Fri, 31 Jul 2026 16:35:44 +0000

Indeed, and maybe that's all there is to it. Still, I'd hope we will eventually better understand what's exactly happening in the wake of many repeated applications of f().

New comment by schmuhblaster in "Handbook.md shows that long policy documents do not reliably govern agents"

schmuhblaster — Thu, 30 Jul 2026 21:41:16 +0000

Yes, I am the author and thanks so much for trying! Please do submit a github issue. My first suspicion about the speed is that maybe an inner loop is taking too many turns until the model finally realizes that a task is finished (so that in turn the runtime knows whether the predicate failed or not and can continue execution accordingly). Happy to take a closer look!

The point about multiline prompts is very valid obviously, that's on the todo list.

New comment by schmuhblaster in "Handbook.md shows that long policy documents do not reliably govern agents"

schmuhblaster — Thu, 30 Jul 2026 15:56:28 +0000

Sorry, did not notice your comment until just now.

So far I am observing two things:

1. For smaller models, performance on Benchmarks such as DeepPlanning does increase significantly.

2. Context hygiene for sub agents becomes much simpler, since that can be expressed relatively concise and the mechanics are handled by the runtime automatically.

Still looking for a good test cases to study possible advantages, but running reliable benchmarks does take time and money...

New comment by schmuhblaster in "Handbook.md shows that long policy documents do not reliably govern agents"

schmuhblaster — Wed, 29 Jul 2026 14:36:06 +0000

For my own (rather idiosyncratic) harness I've been experimenting [0] with "compiling" long markdown specifications into small executable logic programs. It's too early to tell for sure, but I believe that this approach does have its merits when you want some guarantees about how your agents behave for longer tasks.

[0] https://github.com/deepclause/deepclause-sdk