1,857 karma · joined May 8, 2015
rver017@aucklanduni.ac.nz
On the one hand, agents have done this sort of thing for a year+, if you pushed them to check their work. On the other, I absolutely can feel Fable and Sol have crossed a threshold where they can be trusted far more than before. Huge difference between plans written by Opus or Fable.
Accumulated AI slop can simply be cleaned up by better models. Real cost of technical debt is shrinking due to the the inflationary devaluation of code!
For example in search algorithms where you want to search a space without visiting state nodes twice. Each state in the search space is produced by the sequence (a product of) of operators from the start state: elements of a monoid (or group if actions are invertible) which define the primitive steps. Trivial example being generating all permutations of a list. More interesting, enumerate all graphs with some property with pathwidth at most k, by adding one edge or vertex at a time. So now you want to know the structure of this group so you know which sequences of elements simplify and don't need to be tried, and you want to canonicalise each state to throw out duplicates.
And you can think in terms of orbits: if there are some symmetries then you might want to factor by the symmetry group and only visit one node in each orbit, grouping states into orbits with a single representative state. See eg. Pochter, Zohar and Rosenschein, Exploiting Problem Symmetries in State-Based Planners.
HN has lots of hellbanned bots lately (I have showdead on [1]) but I never notice ones pushing a political slant. But I suppose nation states conducting a campaign on Hacker News would be much too cunning to make the bots obvious
[1] because many posts get wrongly flagged, apparently in part by trigger-happy users who will flag anything with incidental similarities to AI prose (everyone, PLEASE STOP DOING THAT), in part because HN's automoderation is severe for new users, and in part because plenty of people get hellbanned either unfairly or although they do still write plenty of worthwhile posts. I even rescued someone who it turned out had been hellbanned by a mod by accident.
Sad but not surprised to hear about all these other issues. I like opencode, it does plenty right but plenty wrong.
Kimi K3 beats each model (out of 35 benchmarks, excluding missing):
vs Fable 5 : 12/35 (34%) (ties: 1)
vs GPT 5.6 Sol : 19/34 (56%) (ties: 1)
vs Opus 4.8 : 30/35 (86%)
vs GPT 5.5 : 30/34 (88%) (ties: 2)
vs GLM-5.2 : 19/19 (100%)
So as more thinking is cached in their weights through increased RL training, those weights are doing more useful work and the efficiency is increasing.
[1] https://www.lesswrong.com/posts/2MD3NMLBPCqPfnfre/cached-tho...
It's very clear from the (excellent) article linked by dang [1] what the exams required:
> This year, the economist decided that both the midterm and the final exams for his course would be of the take-home, closed-book type (there is a certain tradition of this at Ivy League schools). “It’s a very nice kind of exam, because as you’re giving students practically unlimited time to complete it, it lets you make it harder than normal, to see how far they can go.” In this case, Serrano changed some of the model assumptions they had seen in class, and asked students to demonstrate whether certain statements were true or false under the new assumptions.
[1] https://english.elpais.com/education/2026-06-28/ai-fraud-at-...
Seems obvious now that this is the solution. Unfortunately, universities would never agree to downsize, not due to politics or any US-specific problems.
Being serious. "Think about what this might mean..." Finding unexpected links between various ideas and background knowledge. What we call a "novel idea" is virtually always the repurposing of an idea/concept in a new context. A system that maps arbitrary inputs into abstraction spaces in which similarities are discoverable, such as say a deep learning system, is perfect for this.
Any comparisons with other tiny embedding models? Did you start from MiniLM-L6 because it's an especially good model in its class? It's hard to figure this out since all you provide is "Retrieval (SciFact NDCG@10)".
But the claimed performance seems way off, I get only 35 emb/sec in firefox on a i5-4570 rather than 400/sec. Is there an issue with falling back to a non-SIMD path? I'll try a native Rust binary next.
I'm pretty busy, so I only skimmed the article, but it's actually really interesting, and also informative as I'm not familiar with diffusion models. Maybe I'll some ask questions/write later. I do want to encourage you, but, honestly the websites are a bit over the top and there's no way to know how much human input actually went in to them.
Experimental science is very messy, as you've learnt. Agreed with the other commenter, there's value (for others and especially yourself) in writing down what went wrong, and the things in the "Small models cannot judge themselves" is so reminiscent of failure modes I've experienced myself. There are usually awful or subtle bugs, training just doesn't work, and even if the results are "interesting" rather than "bad", it can still be incredibly difficult to decide what to conclude from them. To distill knowledge from observations/experiments is the problem of science. You read papers about experiments seem neat and the results profound, but the truth is they're probably a mess too and the evidence for the conclusions is probably a lot weaker than it looks; ML experiments can be unreproducible too.
I suggest that you were running experiments at too large a scale given your resources: you should try to sort out these critical issues on a smaller scale. Yes, the painful problem with ML is that things change qualitatively with scale, you just don't know if a larger scale will fix your issues. But most of these bugs didn't need scale to discover. Think about how you could have more easily discovered them.
Sorry to tell you that your comment was dead (silently blocked, invisible to most users) until I vouched for it. Don't be discouraged from posting on HN. Clearly both you're a real person, and you wrote this with an LLM (quite understandably), but people are really put off by text that smells LLM generated, and it's really easy to tell. HN is flooded with LLM comments lately, they go dead. You can use an LLM to help write, but don't let it determine the content, be genuine, and make sure it doesn't read like one. They can write in any style.
I've done variants of this a number of times, but feel like it was a generally waste of my time to then have to compare them and write up which parts I liked or disliked: if the output is something substantial, each will have its pros and cons. Clear-cut wins aren't very common. Of course it could work well if we automated the whole thing with an orchestrator; you just need a model with actual good taste (according to your own preferences) ... so we'll have to compare all the models to find that one
Aside, Peter Beck has said (probably at a talk I was at in 2014) that they initially designed and built Electron in NZ so that they would be importing restricted technology into the USA, to minimise ITAR problems, which only covers exports.