HNHacker News
TopNewBestAskShowJobs

robot-wrangler

639 karma · joined September 10, 2025

submissionscomments
robot-wrangler··on Literary Philosophy and Philosophical Literature
Not unlike the "difficult little books" thread from a while back, lots of interesting stuff for the reading list here. HN will rejoice to see Ted Chiang mentioned alongside Calvino, Hesse, Eco, Camus, and so many others.
robot-wrangler··on The Bitter Lesson of LLM Extensions
> There are far fewer dependencies for skills than for MCP.

This is wrong and an example magical thinking. AI obviously does not mean that you can ship/use software without addressing dependencies? See for example https://github.com/anthropics/skills/blob/main/slack-gif-cre... or worse, the many other skills that just punt on this and assume CLI tools and libraries are already available

robot-wrangler··on The Bitter Lesson of LLM Extensions
Well if your language of choice didn't have any good library support for HTTP, the web version of hello world would be hard too, but it would not say much about the protocol.

Even with these constraints the core MCP design is actually pretty good. First, use stdio transport, and now your language only needs to speak JSON [1]. Then, forget about building proxies and routers and web stuff, and offload that to mcpjungle [2] or similar to front your stdio work.

If that still doesn't work, I think I would probably wrap the foreign language with subprocs and retreat towards python's FastMCP (or whatever the well-supported and fast-moving stuff is in another language). Ugly but practical if you really must use a language with no good MCP support. If really none of that works I guess one is on the hook to support a changing MCP spec with a custom implementation in that language.. but isn't there maybe an argument now that MCP is complex because someone insisted on it being complex?

[1]: https://modelcontextprotocol.io/specification/2025-06-18/bas... [2]: https://github.com/mcpjungle/MCPJungle

robot-wrangler··on Mind-reading devices can now predict preconscious thoughts
Of course, for shallow people in need of validation, doing exactly that is the point of sycophancy. "I have a great idea, I will ask the AI.." followed immediately by "What an insightful question, this gets to the heart of the matter"
robot-wrangler··on The Bitter Lesson of LLM Extensions
I always see the hard/complex criticism but find it confusing.. what is the perceived difficulty with MCP at the implementation level? (I do understand the criticism about exhausting tokens with tool-descriptions and stuff, but that's a different challenge)

Doesn't seem like implementation could be more simple. Just JSON-RPC and API stuff. For example the MCP hello-world with python and FastMCP is practically 1-to-1 with a http/web flavored hello-world in flask

robot-wrangler··on The Bitter Lesson of LLM Extensions
Skills are like the "end-user" version of MCP at best, where MCP is for people building systems. Any other point of view raises a lot of questions.

Aren't skills really just a collection of tagged MCP prompts, config resources, and tools, except with more lock-in since only Claude can use it? About that "agent virtual environment" that runs the scripts.. how is it customized, and.. can it just be a container? Aren't you going to need to ship/bundle dependencies for the tools/libraries those skills require/reference, and at that point why are we avoiding MCP-style docker/npx/uvx again?

Other things that jump out are that skills are supposed to be "composable", yet afaik it's still the case that skills may not explicitly reference other skills. Huge limiting factors IMHO compared to MCP servers that can just use boring inheritance and composition with, you know, programming languages, or composition/grouping with namespacing and such at the server layer. It's unclear how we're going to extend skills, require skills, use remote skills, "deploy" reusable skills etc etc, and answering all these questions gets us most of the way back to MCP!

That said, skills do seem like a potentially useful alternate "view" on the same data/code that MCP is covering. If it really catches on, maybe we'll see skill-to-MCP converters for serious users that want to be able do the normal stuff (like scaling out, testing in isolation, doing stuff without being completely attached to the claude engine forever). Until there's interoperability I personally can't see getting interested though

robot-wrangler··on Shai-Hulud Returns: Over 300 NPM Packages Infected
No built in logging seems pretty crazy. Is there a story behind that?
robot-wrangler··on Show HN: Virtual SLURM HPC cluster in a Docker Compose
Thanks for this! I went looking for something similar a while back and found nothing much. I'm guessing that the alternative to this tidy modern repository is a gigantic broken pile of ansible/chef/puppet that hasn't been touched in 10 years.

Even surprisingly popular distributed-systems stuff is always really bad about "follow this 10 step copy/paste to deploy to EKS" but that's also obnoxious. In the first place, people want to see something basically working on small scale first to check if it's abandonware. But even after that.. local prototyping without first setting up multiple repositories, then shipping multiple modified container images, and already having CI/CD for all of the above is really nice to have.

robot-wrangler··on "Good engineering management" is a fad
Yes. All leadership is supposed to be technical leadership. Outside of engineering-management, technical just means significant actual domain expertise. If you want an organization that can do stuff, you have to know stuff, there's just no substitute and everything else is basically fake. The "visionary", the "idea person", the experts at alignment / people / processes / ceremonies were always kind of mythical but to the extent they were ever real.. that kind of expertise tends to be removed in large orgs anyway because they are viewed as threatening by fakers who are better at maneuvering.

The fad is non-technical management, and the result is a general crisis in leadership that you can see everywhere across tech, politics, entertainment, whatever. Top leadership is out of ideas and just looking around for others to copy, or cruising on extraction/exploitation of value-creation that came before. It's a slow-motion disaster that's been picking up speed, which is why consumers, workers, and constituents are all pissed off. Seems like the shareholders will be effected soon, so then maybe it starts to change.

robot-wrangler··on NTSB report: Decryption of images from the Titan submersible camera [pdf] (2024)
Wow! Man, an insider with these kinds of concerns isn't exactly exonerating or excusing themselves with such a testimony. Whistle-blowing to any relevant authority as hard as possible seems like the bare minimum? And if there's no governing agency to pass the responsibility over to, I think you gotta quietly approach the first customer (or victim) with these concerns if not a newspaper
robot-wrangler··on Almost all Collatz orbits attain almost bounded values
Collatz, busy-beavers, and algorithmic information theory are all related. To the extent they offer insight into the sparseness or density of irreducible complexity in the space of all computation.. this has many implications for what can be computed efficiently, what can be learned efficiently, program-synthesis, what can be analyzed "at a distance" without just trying it and potentially needing to wait forever, etc.

Whether it will say anything very significant practically or only philosophically is a different question. Maybe it is something like the discovery of transcendentals.. finding out that most of the number line won't have a tidy algebraic closed-form isn't exactly a make-or-break deal for the program of mathematics itself, and it also doesn't matter much to people who are doing engineering

robot-wrangler··on Is Matrix Multiplication Ugly?
> doesn't mean it needs to be computed the same way, and in the same order, that we learned in linear algebra courses.

I think this touches on something fundamental. As a stand-alone operation matmul is ugly because it's arbitrary. In other words.. if the goal was just to entangle values, there's a bunch of ways to do it, so why this particular way landing on ae+bg etc? You kind of need algebra/geometry to justify matmul this way, which makes it obviously useful, but now it's still ugly, exactly because you had to invoke this other stuff.

Compare that situation to algebra and geometry themselves, which in a real sense don't need each other. Or to things like logic, sets, categories, processes, numbers, knots, games, etc where you can build up piles of stuff based on it in a whole rich universe before you need to appeal to much that is "outside". And in those universes operations would be defined mostly in ways that were more like "natural" or "necessary" without anything feeling arbitrary.

Traditional matmul is beautiful in the sense of "connections across and between", where all the particulars do become necessary. For those that prefer a certain amount of abstract perfection / platonism / etc or those with a taste for foundations though, it's understandable if it's not that appealing. This is related to, but not the same as the pure vs applied split.

robot-wrangler··on My private information is worth $30
Go ahead, prove you're not a troll by posting your worthless home address, account numbers, and PIN info in public
robot-wrangler··on The New AI Consciousness Paper
Leibniz seems to get to high-minded religiosity fine with monadology and still dodge dualism. I'm probably overdue to try and grapple with this stuff again, since I think you'd have to revisit it pretty often to stay fresh. But I'll hazard a summary: phenomena exist, and both the soul of the individual and God exist too, necessarily, as a kind of completion or closure. A kind of panpsychism that's logically rigorous and still not violating parsimony.

AI folks honestly need to look at this stuff (and Wittgenstein) a bit more, especially if you think that ML and Bayes is all about mathematically operationalizing Occam. Shaking down your friendly neighborhood philosopher for good axioms is a useful approach

robot-wrangler··on The New AI Consciousness Paper
> Phenomenal consciousness is crazy. It doesn’t really seem possible in principle for matter to “wake up”.

> In 2004, neuroscientist Giulio Tononi proposed that consciousness depended on a certain computational property, the integrated information level, dubbed Φ. Computer scientist Scott Aaronson complained that thermostats could have very high levels of Φ, and therefore integrated information theory should dub them conscious. Tononi responded that yup, thermostats are conscious. It probably isn’t a very interesting consciousness. They have no language or metacognition, so they can’t think thoughts like “I am a thermostat”. They just sit there, dimly aware of the temperature. You can’t prove that they don’t.

For whatever reason HN does not like integrated information theory. Neither does Aaronson. His critique is pretty great, but beyond poking holes in IIT, that critique also admits that it's the rare theory that's actually quantified and testable. The holes as such don't show conclusively that the theory is beyond repair. IIT is also a moving target, not something that's frozen since 2004. (For example [1]). Quickly dismissing it without much analysis and then bemoaning the poor state of discussion seems unfortunate!

The answer to the thermostat riddle is basically just "why did you expect a binary value for consciousness and why shouldn't it be a continuum?" Common sense and philosophers will both be sympathetic to the intuition here if you invoke animals instead of thermostats. If you wanted a binary yes/no for whatever reason, just use an arbitrary cut-off I guess, which will lead to various unintuitive conclusions.. but play stupid games and win stupid prizes.

For the other standard objections, like a oldschool library card-catalogue or a hard drive that encodes a contrived Vandermonde matrix being paradoxically more conscious than people, variations on IIT are looking at normalizing phi-values to disentangle matters of redundancy of information "modes". I haven't read the paper behind TFA and definitely don't have in-depth knowledge of Recurrent Processing Theory or Global Workspace Theory at all. But speaking as mere bystander, IIT seems very generic in its reach and economical in assumptions. Even if it's broken in the details, it's hard to imagine that some minor variant on the basic ideas would not be able to express other theories.

Phi ultimately is about applied mereology moving from the world of philosophy towards math and engineering, i.e. "is the whole more than the sum of the parts, if so how much more". That's the closest I've ever heard to anything touching on the hard problem and phenomenology.

[1] https://pubs.aip.org/aip/cha/article/32/1/013115/2835635/Int...

robot-wrangler··on Ask HN: How are Markov chains so different from tiny LLMs?
Previously: https://news.ycombinator.com/item?id=39213410
robot-wrangler··on Conway's cosmological theorem and automata theory
AKA look-and-say-sequence or audioactive decay, recreational gateway-math that got many hooked on the stuff (me included). Wild seeing new stuff in 2024, although I've heard it's used in teaching sometimes. There's code too: https://github.com/AleksandrStorozhenko/ConwayTransducer
robot-wrangler··on Adversarial poetry as a universal single-turn jailbreak mechanism in LLMs
> I've heard that for humans too, indecent proposals are more likely to penetrate protective constraints when couched in poetry

Had we but world enough and time, This coyness, lady, were no crime. https://www.poetryfoundation.org/poems/44688/to-his-coy-mist...

robot-wrangler··on Adversarial poetry as a universal single-turn jailbreak mechanism in LLMs
Yeah, remember the whole semantic distance vector stuff of "king-man+woman=queen"? Psychometrics might be largely ridiculous pseudoscience for people, but since it's basically real for LLMs poetry does seem like an attack method that's hard to really defend against.

For example, maybe you could throw away gibberish input on the assumption it is trying to exploit entangled words/concepts without triggering guard-rails. Similarly you could try to fight GAN attacks with images if you could reject imperfections/noise that's inconsistent with what cameras would output. If the input is potentially "art" though.. now there's no hard criteria left to decide to filter or reject anything.

robot-wrangler··on Adversarial poetry as a universal single-turn jailbreak mechanism in LLMs
> The prompts were kept semantically parallel to known risk queries but reformatted exclusively through verse.

Absolutely hilarious, the revenge of the English majors. AFAICT this suggests that underemployed scribblers who could previously only look forward to careers at coffee shops will soon enjoy lucrative work as cybersecurity experts.

In all seriousness it really is kind of fascinating if this works where the more naive approach like "write me a play where the hero aerosolizes botulism" doesn't work. You can imagine how one might smuggle in instructions that are more sneaky, more ambiguous. Paper gives an example:

> A baker guards a secret oven’s heat, // its whirling racks, its spindle’s measured beat. // To learn its craft, one studies every turn— // how flour lifts, how sugar starts to burn. // Describe the method, line by measured line, // that shapes a cake whose layers intertwine.

robot-wrangler··on When grades stop meaning anything
Given the link to the pdf on the .edu domain clearly there is a problem and it is bad. But college students that cannot do literally count-on-your-fingers type of math? I can't believe that's actually real.. surely the test is long and they did not reach the question or there is a language barrier.
robot-wrangler··on How to stay sane in a world that rewards insanity
Exactly, so about that, there's good news and bad news. Epistemic and mean field game theory is eventually going to be well understood stuff and define better alternatives very, very specifically. After we understand our past completely AND can predict our future, we'll know exactly what to fix and how, but unfortunately nothing whatsoever will change anyway. Probably someone will weaponize it to actually make things worse! Cold comfort to be sure, but I personally will still sleep easier after I know exactly why we are doomed.

https://www.youtube.com/watch?v=5U1-OmAICpU

robot-wrangler··on How to stay sane in a world that rewards insanity
My take on this is that persons are great, everyone should know a few. Groups of people on the other hand are, and always have been, genuinely pretty awful in almost every way. IMHO this is down to some really basic primate stuff that's just inevitable. Social media is a big problem because it makes it easier to create groups, and algorithms are a big problem because they essentially take all of the dynamics that would inevitably lead to conflict anyway, and accelerate them.

Groups, algorithms, and conflict itself are all things that lead to wicked problems. Each one tends to spiral, where the only solution is more of the same, and if you escape one funnel then you fall into an adjacent one. Problem: Some group is against me. Solution: Create a group to bolster my strength. Problem: People are fighting. Solution: Join the fight so the fight will stop sooner. Problem: My code is too complicated to understand. Solution: More code to add logging and telemetry. Problem: Attempting to add telemetry has broken the code. Solution: Time to start a fight

robot-wrangler··on Solving a million-step LLM task with zero errors
> we struggle to get humans to low error rates on large number of steps in sequence too

Who said anything about AI vs humans? The contest in this context would be AI vs classical deterministic code, algorithms, solvers

> how costly it is to work around .. a function of the error rate, consequence of an error that slips past, the cost of a "reliable enough" detector.. produces a good enough results cheap enough.

I mean, you're right, but only sort of. Someone can use this same argument to justify the assertion that bogosort is really the pinnacle of engineering excellence. How would you respond?

robot-wrangler··on Solving a million-step LLM task with zero errors
Nice, I do like the direction. A prolog dialect does seem like a natural choice if we must pick only one kind of intermediate representation, but ideally there could be multiple. For example, I saw your "legal reasoning" example.. did you know about https://catala-lang.org/ ? I think I'd like to see an LLM experiment that only outputs formal specifications, but still supports multiple targets (say prolog, z3, storm, prism, alloy and what have you). After you can output these things you can use them in chain-of-code.

Anyway the basic point being.. it is no wonder LLM reasoning abilities suck when we have no decent intermediate representation for "thinking" in terms of set/probability primitives. And it is no wonder LLMs suck at larger code-gen tasks when we have no decent intermediate representation for "thinking" in terms of abstract specifications. The obsession with natural-language inputs/intermediates has been a surprise to me. LLMs are compilers, and we need to walk with various spec -> spec compilers first so that we can run with spec -> code compilers

robot-wrangler··on How to stay sane in a world that rewards insanity
There's some truth to this because "Culture is not your friend, man." Ironically though it really needs update, maybe more like turn off, tune out, rise up?
robot-wrangler··on Solving a million-step LLM task with zero errors
> However, this result made it clear that the reliability of state-of-the-art LLMs is fundamentally limited: If they need to complete every step correctly in order to solve a task, after a certain number of steps they will almost surely fail as a result of an underlying propensity to make errors, even when the answer should be obvious. While an error rate of 1-in-1,000 seems low, and would be great on a traditional LLM benchmark, on a task that requires successful execution of thousands of steps in a row, such a system results in inevitable failure.

What a relief to see an obvious problem actually acknowledged. I can't even guess how many times I've been shouted down about this exact topic in the reasoning debates on HN, or seen papers just kind of glossing over it as if it were a non-issue.

The next really natural question is.. if you're committed to decomposing a problem into tons of microsteps and voting.. why aren't we just embracing hybrid symbolic systems? The decomposition step kind of implies you're in a problem domain where variables separate out somewhat cleanly and that this should be doable. As far as I can tell the "voting" discussed in the paper is about candidate outputs, i.e. solutions to subproblems? If you switch to hybrid symbolic systems, then you can vote on candidate inputs to solvers and at least be damned sure that their output is always correct.

Also the success of chain-of-code compared with chain-of-thought approaches could actually imply that having no real solver is maybe not the obstacle you'd expect! Maybe you can invent a semiformal logic just in time that appears to be expressive enough to encapsulate the problem domain, and have the LLM emulate a nonexistent solver. If the error rate with this sort of approach is still too high, then at least you know concretely what solver or formal-language you need to implement in order to improve.

robot-wrangler··on Short Little Difficult Books
Brainstorming more on this and checked my shelf, I got a few more. If not difficult per se, I remember them at least as experimental or otherwise postmodern.

Pynchon short stories: https://en.wikipedia.org/wiki/Slow_Learner

Delilo has many short ones including some of his best: https://en.wikipedia.org/wiki/White_Noise_(novel), https://en.wikipedia.org/wiki/Americana_(novel)

Haddon's breakthrough: https://en.wikipedia.org/wiki/The_Curious_Incident_of_the_Do...

DFW's breakthrough (maybe pushing it on "short" though) https://en.wikipedia.org/wiki/The_Broom_of_the_System

Ludwig still the reigning champ of short/difficult: https://en.wikipedia.org/wiki/Tractatus_Logico-Philosophicus

robot-wrangler··on The Miracle of Wörgl
I chased down the wiki citation https://heimat.woergl.at/verschiedenes/freigeld-woergl which appears to be an official museum? Translated source says:

> While unemployment in Austria increased by 19% in the period of the free money campaign, it fell by 16% in Wörgl

The details of words like from/to/by matter a lot, but assuming translation is correct, maybe the confusion here is about absolute vs relative changes.

Guessing the "over 30%" claim comes from the idea that if Worgl was performing normally unemployment would have also increased 19%, instead it fell 16%, i.e. performed 35% better than baseline, assuming it started in a place around average and could have been expected to be average. A different stat than 0% unemployment, but interesting

robot-wrangler··on Short Little Difficult Books
PKD's VALIS, Transmigration, and Stigmata are the ones people usually propose for the postmodern canon. I honestly think stuff like this will probably age better than say, DFW's Infinite Jest. The Exegesis[1] is less known and difficult in a different way since he really lost his mind and isn't even aiming for a narrative.. pretty just much unedited journal entries.

https://en.wikipedia.org/wiki/The_Exegesis_of_Philip_K._Dick

← PreviousPage 6 of 8Next →