HN user
That is easily fixable with the "Instructions for Claude" in your settings. Just put:
"be critical, but correct. I don't want affirmation, i want to actually accomplish things."
I don't get any sycophancy from it. The conversations are actually quite good, and it'll push back if it thinks I'm wrong.
It has an MIT License
It happened to my father, who was suffering a severe mental decline because of hydrocephalus. After weeks of trying to figure out what happened, one day he was sitting in the hospital perfectly fine, talking normally. I remember being so relieved. But then the next day he was back to not knowing anything and being half aware. He died a few weeks later.
There's meaning in the term "car wash" that it understands. But I don't suspect anyone has taught it that for 99.9% of people, going to car wash ONLY means that you're going to wash your car and that it should make that implicit assumption.
What if you're the car wash owner? Or a maintenance technician? Pretty easy to just walk over there if you're just 50ft away.
uncover blockers that people haven’t surfaced on their own
I constantly reiterate to people, whether they're reporting to me or not, that they need to speak up when there's a blocker. I feel its a very telling skill of engineers whether or not they can communicate issues in an effective manner urgently and figure out the best course of action to unblock.
I've heard tales of 300k/yr engineers that just sit there and wait for a manager to ask if they're blocked, or just sit there until they're told what to do.
Plenty of evidence has been found. For one, the US government has leaked/released a video showing instant acceleration of a flying object. Nothing on earth can do that.
Why not?
Last year, there was a period of a week or two where I would see Gemini responses diffusing in. I don't know if they were experimenting with it, or if it was just an effect. It didn't last long, but it was interesting to see.
I built an algorithmic trader years ago just using Python, but for the hot paths I gave each algorithm its own function in its own file, and then I would compile the files with Cython. The speedup was pretty significant. I barely wrote any "Cython" stuff (meaning declaring variables and other minor assists). The code is still very much python, just with a few little extras that are easy to understand.
Inaccurate rescues - jobs that are long-running might get rescued even if the producer is still alive. Pro version uses smarter heartbeats to track producer liveness.
So the non-paid version really can't be used for production unless you know for sure you'll have very short jobs?
You may find this study useful: https://www.nature.com/articles/s41586-025-09335-x
I've begun taking very small amounts of lithium orotate (5mg), among many other preventative measures.
From multiple personal experiences, including both of my parents, dementia is a slow, horrible death where you are robbed of your dignity and end up dragging all of your relatives through a very long, very torturous hell. You will be drooling, pissing, and shitting yourself, all while slowly reverting back to a low IQ childhood mentality where you're very likely to have outbursts and verbally or physically attack the people around you. Your loved ones will be tormented, and if you don't have loved ones then if you're lucky you'll be tossed into a room and forgotten about by underpaid, overworked staff at some run-down nursing home. If you're not lucky you'll be laying in a gutter on the street until you die.
Yeah they looked at 120 people age 71 and above for that study. By that point its a little late.
Taking valacyclovir should help prevent or delay as well.
That makes sense. And its even worse of a reason. At least for people living in the US.
Ok so a few thoughts as a former Seattleite:
1. You were a therapy session for her. Her negativity was about the layoffs.
2. FAANG companies dramatically overhired for years and are using AI as an excuse for layoffs.
3. AI scene in Seattle is pretty good, but as with everywhere else was/is a victim of the AI hype. I see estimates of the hype being dead in a year. AI won't be dead, but throwing money at the whatever Uber-for-pets-AI-ly idea pops up won't happen.
4. I don't think people hate AI, they hate the hype.
Anyways, your app actually does sound interesting so I signed up for it.
For input,
- GPT-5.1 is $1.25 / 1M tokens
- You are $0.50 / 1,000 tokens
Output:
- GPT-5.1 is $10.00 / 1M tokens
- You are $1.50 / 1,000 tokens
Am I reading that wrong? Is that a typo?
I had terrible anxiety as a child and what I experienced dramatically affected the core of who I am. It is engrained in me and I struggle with it daily, though after decades I have surpassed a good portion of it. If a small dose can help someone have a somewhat "normal" childhood, then its worth a try.
I think you're missing a more human point: people dislike the effect of hiring and firing thousands of people with zero consideration. They hire thousands because it makes management look like they're ramping up to solve problems, and then they fire this many people because it makes management look like they're cutting costs to be more efficient. It's all about management keeping up the illusion that they're "on top of things", when in reality they're just playing number games.
There's empathy involved in the revulsion toward this kind of process. Please take time to consider that not everyone fired is a $300k/year rockstar programmer who can just as easily walk over to Meta or Google for a job. I know of people who have uprooted their lives and work under the idea that if they do a good job they'll stay on, when in fact the reality is more like gambling and they could be fired at any point.
I pulled myself from a recent Amazon interview process because of how bad they are. At first I had the opinion that this could be interesting and exciting, but the more I thought about how they treated people, the more I realized that the internal culture must be terrible. And honestly I just don't need to be involved with any of that.
Sounds like those ML "scientists" were actually just engineers.
How does this fair with the Vidore benchmark?
If the herpes virus can increase the odds of getting Alzheimer's, then taking valacyclovir is another thing that can be done to reduce the odds.
The IRS does have a free filing service called Direct File: https://directfile.irs.gov/
The Trump Administration is trying to get rid of it, but its been so successful and so well-rated that they're having trouble doing that.
They do, IRS Direct File: https://directfile.irs.gov/
At my last job, whenever a commit wouldn't build, we would blast it into a slack channel with an alert that included the comment and the name of the developer.
Democrats are cowards and will not stand up against any of this.
They're making a lot of money in the stock market due to their position, they won't jeopardize it.
DOGE may not be the right answer, but it's the first actual reduction in spending in my lifetime
On what timeline? The week of the first round of RIFs? The first month?
I assure you, as someone who works with in the space where DOGE has played, it will NOT be a reduction in costs in the long run. In fact, costs will go up because of the indiscriminate nature of "cost reduction". When the only people with knowledge of a system are removed, the remaining people cannot run it - no matter what AI they are given. At that point, you have to either hire back the people you fired, with a serious delay of important work, or you stumble for years until it can be figured out at the cost of delays, protests, lawsuits, whatever.
Considering firing everyone a reduction in costs is a shallow, short-term view.
Safety is a huge concern with construction and really any operation that uses heavy equipment. I promise you they all know about Tesla autopilot running into people and will absolutely bring it up ad nauseum.
And I only say this because I think this is an interesting area to pursue so I hope you're successful with it. But a focus on safety will be of paramount importance.
How much safety training have you done with the models? i.e. does it know to stop if it's about to drive over a human?