Hacker News: schmuhblaster

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

Loops? Graphs? Prolog!

schmuhblaster — Sat, 25 Jul 2026 20:21:55 +0000

Article URL: https://deepclause.substack.com/p/loops-graphs-prolog

Comments URL: https://news.ycombinator.com/item?id=49051159

Points: 3

# Comments: 0

New comment by schmuhblaster in "Towards a harness that can do anything"

schmuhblaster — Fri, 17 Jul 2026 20:50:19 +0000

You might like this: https://github.com/deepclause/deepclause-sdk.

It’s a DSL I’ve been working on to encode mixed deterministic/probabilisitic agent behavior.

New comment by schmuhblaster in "Meta caps internal AI token spending"

schmuhblaster — Thu, 02 Jul 2026 02:54:22 +0000

Been building various LLM+PDF pipelines at work. As soon as you need to e.g. parse tables etc. it becomes a lot of hard work!

New comment by schmuhblaster in "America can switch off AI. Europe must switch gears before it's too late"

schmuhblaster — Wed, 01 Jul 2026 07:38:39 +0000

As a European I have long given up on any meaningful change w.r.t AI. Imho the average European is much more risk averse than the average American or Chinese. That and a plethora of other factors that have been discussed over and over again, make it unlikely that we'll see things change within the next ten years or so. Only massive and immediate threats (e.g. he crisis in Ukraine) will make people and governments reconsider their fundamental beliefs (and even then the pace of change will be slow).

New comment by schmuhblaster in "Kb – Prolog Knowledge Base"

schmuhblaster — Tue, 30 Jun 2026 08:32:42 +0000

Awesome work! If I understand it correctly, it loads relevant subgraphs from the DB and then runs queries in Prolog on it? Or is it more similar to datalog?

New comment by schmuhblaster in "Qwen 3.6 27B is the sweet spot for local development"

schmuhblaster — Tue, 30 Jun 2026 07:09:20 +0000

It's my own (slightly idiosyncractic ;-) harness: https://github.com/deepclause/deepclause-sdk

New comment by schmuhblaster in "Qwen 3.6 27B is the sweet spot for local development"

schmuhblaster — Tue, 30 Jun 2026 06:33:53 +0000

I've worked extensively with the slightly less able cousin, the 35B A3B model and tuned my own harness around making it work well with local or non-sota models. The results are quite promising [0], if one sticks to a plan-execute approach. After a bit of fiddling with llama.cpp I was able to get it to work through a small change on a real codebase from work on a 32GB M5 (typical python FastAPI backend, so nothing out of the ordinary). While that's somewhat encouraging, the whole local experience was still far from pleasant with all the noise and heat.

[0] https://deepclause.substack.com/p/how-to-make-small-models-p...

Getting LLMs Drunk to Find Remote Linux Kernel OOB Writes (and More)

schmuhblaster — Sat, 27 Jun 2026 09:46:53 +0000

Article URL: https://heyitsas.im/posts/drinking-llms/

Comments URL: https://news.ycombinator.com/item?id=48696719

Points: 2

# Comments: 0

New comment by schmuhblaster in "AI in mathematics is forcing big questions"

schmuhblaster — Sat, 27 Jun 2026 06:16:09 +0000

Mathematics has always been an experimental science to some extent. While Newton, Euler and Gauss would spend a lot time calculating numerical approximations by hand, modern mathematicians have been doing the same using computers and software. And once an a clear picture emerge about what’s going, you can start to formalize that and attempt to prove and communicate your results in the standard definition, proposition, lemma, theorem scheme. (Btw there is even a journal called Experimental Mathematics devoted to this approach).

I don’t see that LLMs will fundamentally change this, but rather accelerate the speed of mathematical research.

Some computer generated proofs might of course be hard to understand, but at least their existence gives another data point work with.

Doing Mathematics is more than proving something, that’s just the end of a long road spent pondering at one’s desk about how things could work out.

New comment by schmuhblaster in "Puzzling Success of Overparameterization: Lottery Tickets or Escape Dimensions?"

schmuhblaster — Thu, 25 Jun 2026 16:13:40 +0000

> This trend dates back at least to the machine learning bible, Elements of Statistical Learning (2001).

Could you elaborate on this?

New comment by schmuhblaster in "For Most of the World, Open-Source AI Is the Only Way Forward"

schmuhblaster — Wed, 24 Jun 2026 17:31:42 +0000

Indeed, and with some tinkering around the harness it can even punch way above its weight.