HNHacker News
TopNewBestAskShowJobs

withinboredom

8,711 karma · joined October 16, 2016

[ my public key: https://keybase.io/withinboredom; my proof: https://keybase.io/withinboredom/sigs/73lKYnYnXl8zj6I5he8z9w__Y_egIUOa-zxiXwaFMDE ]

email me at landers dot robert at gmail

submissionscomments
withinboredom··on Constraint Decay: The Fragility of LLM Agents in Back End Code Generation
Saying that it’s dismissive is like saying writing (insert language) is dismissive that you’re just writing assembly.

at the end of the day, it presents a vector field and predicts the next vector. That’s literally the heart of intelligence just like assembly is the heart of execution. When playing table tennis, your brain is literally predicting seconds into the future to get your body into the right position.

But we aren’t discussing intelligence here. We are discussing how best to utilize that intelligence.

withinboredom··on Constraint Decay: The Fragility of LLM Agents in Back End Code Generation
Doesn't that make sense? Its text prediction. If you give it examples, it can predict. Synthesizing "put semi-colons on new lines" requires it to generate its own examples 'in its head' (so to speak) and remember that. It won't.

It's like when I see people feeding it a whole bunch of "best practices" and expect it to follow them. It won't. But you could ask it questions about the best practices all day long.

withinboredom··on What is the history of the ERROR_ARENA_TRASHED error code?
Bitflips are surprisingly more common than you think but rare enough to not be a concern.
withinboredom··on Archaeologists find Egyptian mummy buried with the 'Iliad'
I am a fan of the Beatles. What’s wrong with that?
withinboredom··on An OpenAI model has disproved a central conjecture in discrete geometry
Well. Sure. If we move the goal post to “something passable and good enough” you only need a small number of people. In that sense, we are lucky that “black smithing” (as a proper trade) only ended in the last hundred years and many people continue it as a hobby. In that case, “small team of hobbyists” can likely reproduce a few bricks. But bootstrapping mass production of bricks? Unlikely.
withinboredom··on An OpenAI model has disproved a central conjecture in discrete geometry
> That is fascinating how the more knowledge and reasoning we can get our hands on and actually produce, the higher the risk of us, as a species, to become actually much dumber.

This has always been true. There was a time where someone had to teach farming to others and that information had to spread and be passed down. Eventually, farmers became better than hunter-gatherers and they became known as hunters. The information on what was safe to gather for civilisation got passed down as 'safe to eat on the hunt' because the farmers were farming. The civilisation collectively "forgets" foraged foods as that knowledge becomes niche.

Does that mean we got dumber?

withinboredom··on An OpenAI model has disproved a central conjecture in discrete geometry
Sorta. Take a look at a brick in a house. You'd need everyone from geologists to miners to kiln specialists to construction workers and engineers -- not to mention all the people required to make the tools required to make the tools. The team would likely involve well over 1000 people. So, "just assemble a team" is not quite as simple as you make it sound.
withinboredom··on New arXiv policy: 1-year ban for hallucinated references
Even as a human, you can still fuck up references.

I submitted a paper with a reference author as Elisio because I couldn’t read my own handwriting. After submitting, I double checked all the references through an LLM. It pointed out that their name was actually Enrique. Yes, you should probably double check your references before submitting, not after.

Point is, I didn’t even trust the LLM at first. But after verifying the mistake, I was embarrassed af. I resubmitted with the fixes before it went live, but ultimately, what’s the difference between “mistake” and “hallucination”?

withinboredom··on Show HN: Startup Equity Adventure Game
You can borrow against your shares if you have a good relationship with the bank. That will allow you to be wealthy enough to buy some shares in the round. Not enough that you won't get diluted, but not as much as being broke. And of course, you have to pay back the loan.
withinboredom··on The Road to a Billion-Token Context
"type problems" was doing the heavy lifting there, not literally "this utility".
withinboredom··on Security through obscurity is not bad
Gazelle bikes are pretty fast ... instructions unclear.
withinboredom··on The Road to a Billion-Token Context
For larger codebases ... maybe it will cut down on "let me create a random number wrapper for the 15th time" type problems.
withinboredom··on Talkie: a 13B vintage language model from 1930
Ask it about the aether as well. I think it was disproven around that time.
withinboredom··on An AI agent deleted our production database. The agent's confession is below
> What was being discussed wasn't some specific molecular process, it was the false premise "oh molecules move around randomly so your ceiling might just collapse of its own accord because the beam decided to randomly disintegrate". That's not something that happens.

Except it does happens. That’s why buildings get condemned and buildings eventually turn to rubble.

To the exact point; I have a product from a couple years ago using an old model from OpenAI. It’s still running and all it does is write a personality report based on scores from the test. I can’t update the model without seriously rewriting the entire prompt system, but the model has degraded over the years as well. Ergo, my product has degraded of its own accord and there is nearly nothing I can do about it. My only choice is to basically finagle newer models into giving the correct output; but they hallucinate at much higher rates than older models.

withinboredom··on An AI agent deleted our production database. The agent's confession is below
I've had a ceiling fall on me once and once to a friend while on vacation. Just because it hasn't happened to you doesn't mean it hasn't happened to other people.
withinboredom··on Show HN: Startup Equity Adventure Game
Yeah, also seems very US-centric with "outstanding shares". Other countries don't allow you to have outstanding shares. Also, where is the "reinvest" option during series rounds. Like, what founder also doesn't reinvest to keep their equity during fund raising?
withinboredom··on I bought Friendster for $30k – Here's what I'm doing with it
I can only imagine someone looking over my shoulder on vacation to see what I'm posting: "oh, you have a 'close friends' group; why am I not in it?"

Arbitrary labels are great ... until they're not.

withinboredom··on Astronomers find the edge of the Milky Way
Thanks. Cloudflare took so long to determine whether or not I was bot-shaped that I just came to the comments.
withinboredom··on Qwen3.6-35B-A3B: Agentic coding power, now open to all
He literally said it came down to the comment in the SVG. Points for taste, not correctness. Basically.
withinboredom··on GitHub Stacked PRs
Judging by the amount of adults wandering around thinking their personal problems are everyone else’s problem… they were pretty good teachers.
withinboredom··on N-Day-Bench – Can LLMs find real vulnerabilities in real codebases?
I didn’t read tfa, but can we also have it be able to distinguish when a vulnerability doesn’t apply? As an open source contributor, people open nonsensical security issues all the time. It’s getting annoying.
withinboredom··on GitHub Stacked PRs
Sounds like what my teachers used to say: “a personal problem”. Literally nobody outside FB knows what they’re missing and until they fix that, literally nobody cares.
withinboredom··on We have a 99% email reputation, but Gmail disagrees
When I worked on a notification system that sent over a billion messages a month. We received spam complaints on emails sent 6+ years ago. No correlation, just a one-off spam complaint. I always wondered why this was happening.
withinboredom··on Are We Idiocracy Yet?
Are you serious? Like, actually serious?

Killing someone for pushing you over is not "self defense". This is a category error.

withinboredom··on We've raised $17M to build what comes after Git
It’s always under the most annoying thing to move or get to. Under table legs, couches, etc.

Also, Lego will send you any missing pieces for free.

withinboredom··on We've raised $17M to build what comes after Git
You need to get some bins that have a top shelf like a toolbox. The low item counts go in the top shelf, segregate the bottom for efficiency. Bin by color.
withinboredom··on Claude Code login fails with OAuth timeout on Windows
I feel this sentiment. It’s more like pair programming with someone both smarter and dumber than you. If you’re reviewing the code it is putting down, you’re likely to spot what it’s getting wrong and discussing it.

What I don’t understand, are the people who let it go over night or with whole “agent teams” working on software. I have no idea how they trust any of it.

withinboredom··on Are We Idiocracy Yet?
Ok. Now this is logic I understand. Nobody is saying you don’t have a right to self defense. The question should be: why do you have a right to bring a gun to a fist fight?
withinboredom··on Issue: Claude Code is unusable for complex engineering tasks with Feb updates
Interesting. So literally triggering any of these changes probably invalidates the cache as well…
withinboredom··on Are We Idiocracy Yet?
I have no clue what I just read or what kind of mental gymnastics are required to say that a right to a weapon overrides a right to live.

It used to blow my mind when I moved here (Netherlands) that I wasn't allowed to use a weapon to defend myself... but then you realize ... basically nobody has weapons.

← PreviousPage 2 of 34Next →