HNHacker News
TopNewBestAskShowJobs

mwigdahl

1,303 karma · joined July 18, 2017

submissionscomments
mwigdahl··on Finger: the 1971 social network that never died
In the late 80s, a friend of mine broke up with his girlfriend via email while they were both sitting in the same computer lab.
mwigdahl··on Linear algebra done right
What do folks think of Hefferon's _Linear Algebra_?
mwigdahl··on Learning more about Claude's mathematical capabilities
I don’t think it’s absurd. We’ve created these things, however alien the structure, with as much human text as we can scrounge up and jam into them.

Text is an imperfect distillation of the human experience, but it doesn’t surprise me that a machine trained on human text responds to human encouragement.

mwigdahl··on Assembly Hall of Shame
Wirth's Law I believe.
mwigdahl··on The Shape of Things to Come
"Beads is the best. If you're not using Beads, you're failing. Gas Town, which I have just told you was a failure, was built on Beads. Gas City, which also failed, was also built on Beads. Wheelhouse, which I'm working on now and will be awesome? Beads. Therefore you should use Beads."
mwigdahl··on MiniMax H3 Day-0 Support in ComfyUI: Open Weights, Native Audio, and 2K Video
If you wouldn't mind sharing, what's your Comfy workflow for this? I have the same video card setup and would like to give it a shot.
mwigdahl··on The End of an Era
I don't buy it, although I agree with GP's larger point about other strengths.

Printing presses are about exact duplication of writing. The internet is a higher layer printing press. LLMs substitute for (some of) the human effort of producing the text that a printing press or the internet can then replicate.

mwigdahl··on What it means for an API to be RESTful
Nice! Not 100% sure, but it reads very human to me. The only LLM-ism that jumped out at me was "An honest note before we continue", but that was the only time the word "honest" appeared. If it's not human-written it does an exceptionally good job of appearing so.
mwigdahl··on What it means for an API to be RESTful
Well, this inevitable flamewar will be a nice change from the pro-AI / anti-AI comment threads, at least...
mwigdahl··on A Trampoline
You just keep right on driving...
mwigdahl··on Kalshi attacks a Wisconsin law banning election bets as 'voter suppression'
There's big money in it, so of course there's going to be a huge PR push to cast it as a great moral and societal good.

The thing that gets me is that the rationalists who were such outspoken proponents of prediction markets (look up "futarchy" and the many positive articles about it) failed to predict the astonishing amounts of corruption that have come along for the ride with them.

mwigdahl··on Handbook.md shows that long policy documents do not reliably govern agents
Sure! I use an orchestrator main agent whose only job is to run subagents through the workflow process I've defined. Part of that workflow is to invoke a review subagent at particular points to check the spec, the implementation plan, and the code for rule conformance.

The review subagent has its own definition and gets invoked with a specific target, so the context is very focused on just rule enforcement and I don't have problems with it skipping rules.

The whole workflow is packaged up as a plugin, but you don't need that to get this approach to work. It should be sufficient to have the rules you want enforced written out somewhere, and to either kick off a focused review agent manually referencing them, or do something like I did and have it be a defined part of your workflow (depending on the automation level you want).

mwigdahl··on Handbook.md shows that long policy documents do not reliably govern agents
Subagents whose only job is to review the actions of your other agents for rule compliance? It works reasonably well for me in complex workflows using Claude Code.
mwigdahl··on Kalshi attacks a Wisconsin law banning election bets as 'voter suppression'
And to note, the law in question is from the 1800s -- hardly something novel Wisconsin is doing.
mwigdahl··on AI companies are shredding rare books
The book clearly and repeatedly makes the point that immersion in ubiquitous computing made the younger generation smarter and quicker than their forebears. Miri was 13 and Juan was, what, 9? Both were depicted as running rings around the older generation, even those who weren't taken out of action like Robert.

The form and maybe even the content of electronics in school may echo, sure, but the results sure don't.

mwigdahl··on Discovering Cryptographic Weaknesses with Claude
Do you really think that if a Chinese model had achieved a significant math breakthrough that it wouldn't be trumpeted to the global media? The "Deepseek moment" was great for China; this would be the same.
mwigdahl··on AI companies are shredding rare books
Well, an oracle except for that part in the same book where unlimited access to the internet made all children prodigies self-motivated by their love of learning.
mwigdahl··on Nvidia, Microsoft, Meta warn against overregulating open-weight models
The fully loaded cost of employees at that salary level is likely over $100K. You may still be right on the relative expenses, but you can't just look at the top-level salary line.
mwigdahl··on Xiaomi-Robotics-1
Sure, but the original comment said "living out" those fantasies.
mwigdahl··on Fable 5 dropped from subscriptions before the promised July 19 date
I don't know -- it's not even showing Fable in /usage any more, in sessions that were using it just fine moments before. Seems more like a backend change to me.
mwigdahl··on What's the most popular number in Hacker News titles?
You missed a great opportunity to title this "The 10 most popular numbers in Hacker News titles"!
mwigdahl··on Ask HN: Any objective research on which languages are best for AI agents?
For sure! It's possible there are relatively invariant properties that make one language or another "better" for LLM coding in general though (even if that's just the self-fulfilling prophecy of size of the training corpus).
mwigdahl··on AI content is everywhere on social media, especially LinkedIn
“An honest caveat…”
mwigdahl··on GLM 5.2 and the coming AI margin collapse
There were a lot of European wars between the Napoleonic Wars and the First World War. I agree with your point overall but there was a lot of fighting each other during that timeframe.
mwigdahl··on Ask HN: Fable 5 promo ends today – is anyone keeping it once it's usage-billed?
Yes. It is great for analysis, debugging, and understanding larger segments of code. I'll use it sparingly since it won't be on subscription, but there are cases where it will make sense to use it.
mwigdahl··on 2026 Unslop AI-Written Fiction Contest Results
I'm reading your story now -- it's great space adventure! Congratulations!
mwigdahl··on Don't give Fable all the power
Apparently Fable got all the power when writing this...
mwigdahl··on Anthropic's Method to Losing Goodwill in a Few Easy Steps
> Fable returning wrong answers if it suspects the topic is sensative

Citation, please? On the original release they downgraded models silently to Opus 4.8 when they suspected it was being used for LLM development, but they stopped doing that. Now when you hit one of the guardrail subjects it downgrades to Opus 4.8 visibly in all cases.

I've never seen anything suggesting they're deliberately returning wrong answers. Maybe you're thinking of Gemini's anti-distillation tech?

mwigdahl··on Asymmetric Quantization: Near-Lossless Retrieval with 97% Storage Reduction
Unfortunately as cost reduction trends to 100%, it comes along with an intrinsic high-pass sarcasm filter.
mwigdahl··on CursorBench 3.1
Same (including the overthinking issue).
← PreviousPage 2 of 16Next →