Mine does too because, while I use Codex, my non-technical co-founder uses Claude. I find Claude still will randomly ignore instructions in there. Basic things like how to name a PR or what to put in a PR description.
My experience is that what you're suggesting isn't a perfect solution.
No. I'm saying that the pattern of having one instruction file that just says "read this other file" doesn't seem to work well. Having a CLAUDE.md that just says "Read AGENTS.md" resulted in Claude randomly not following the rules. We tried the other way and it didn't seem like it was any better, but also, given that AGENTS.md is the standard everywhere except for Claude Code, I don't really want CLAUDE.md to be the source of truth
> Modern tech workers arguably have the best career deal in the history of humankind. I see no upside in killing the goose with the golden egg.
I agree, but that's actually one of the strongest arguments for why tech workers should unionize now. Wages are high because employees have leverage due to 10-15 years of demand for skilled workers being higher than supply. If you wait until that leverage is gone to form a union then you've lost a lot of the leverage to negotiate for better conditions as a union.
For the record, I've been in a union in another industry much earlier in my career, and I'm pretty on the fence about a tech workers union, but I think your argument is pretty short sighted.
I've come to the same conclusion over and over with all of the Chinese models that have been claimed to be catching up with OpenAI's and Anthropic's frontier models (Deepseek 4, GLM 5.2, Kimi K3).
At their best, I think they're closing in on Opus and GPT, but they're incredibly inconsistent and the variance in output quality is much higher than the best from any of the Anthropic or OpenAI models from the last few generations. The only way I can describe it is that it feels like a lack of intuition with the models which means I find my self needing to write longer prompts or have more back and forth to get them to do what I want from them.
To give an example, I have a saved prompt that I use as a sanity check on some data I'm storing. It reads about 50 rows from a DB and matches them to the UI and makes sure the data is displaying correctly. I've been using this with GPT 5.5 and now 5.6 for a few months and running it a few times a week with no issue. Sometimes I'll run it multiple times in a single chat if I notice bad data (run it, fix thing, run again, fix another thing).
I recently tried to switch to using Deepseek v4 (first flash and then pro) and while both did the task just fine, both would do things like change the response format from one message to another in the same chat or randomly decide to omit things it didn't think were relevant. At one point I ran the prompt, fixed some bad data, and then said "Okay, I fixed row 7, run {prompt} again" and so it decided to leave row 7 out of the response. A few times the first message would contain a table and then the next run in the same chat would contain the data in a bulleted list.
None of those are major issues and all could be solved with a bit more rigor in my prompting, but for me it makes them harder to work with. Those examples are a bit trivial, I think they're the easiest way for me to illustrate the gaps I see with them.
Seattle was announced as a Waymo upcoming city nearly 2 months before Houston, gets a foot less of rain than Houston each year, and usually has only 2 or 3 snow days a year. That's at least one counter example to your theory.
Usually if you're working a stressful, low paying, dangerous job it's because you don't have many other options. I'm pretty sure "just get another job" is easier said than done for most Uber drivers
I think Uber is openly stressful, but is not transparently low paying or dangerous and that is why people are working it. On face value, it seems easy to earn with your existing vehicle, but most drivers dramatically overestimate earnings after depreciation, fuel, maintenance on their vehicle. Additionally, Uber puts the driver in the most dangerous situations (pickups and drops on active roadways) which aren't apparent to the driver. Driving for 6 hours a day will eventually wear on you.
So, yes, I think drivers severely underestimate the risks and rewards and that is why another job is likely better (which is loosely defined here)
I don't think the person you're responding to was trying to deny global warming being a factor. I think they're just explaining why this fire is so bad compared to other fires we have seen in France before.
I know global warming plays a major role in this, but I still found it interesting to know why this fire seems so bad.
You may be absolutely right about the OP, I cannot know.
Still, I believe it is important to highlight the elephant in the room first.
For example to your point: "I still found it interesting to kmow why this fire seems so bad compared to [...] before", I think it is important to state: "because global warming is getting worse over time". Not because pine trees, which have been around for a long time, and have never burned so badly.
The elephant in the room is that many of those fires are criminal and that the French government has arbitrated budget restrictions against investing in fire-fighting equipment, especially planes.
It so happens that the current fire near Bordeaux is roughy in the same area as the historic fire of 1949 in which 82 people died (and currently still smaller, hopefully it will stay that way) [1], as someone else already mentioned.
Wildfires in Fontainebleau are not new, either, even if this year's one it is historically large. First laws against fires in the in forest and obligation of inhabitants to help in case of fire date from the 14th century [2].
Yes warming trends do not help and increase risk (hence need to invest in equipment and prevention) but there is also fabricated drama and lack of perspective, which are unfortunately how everything is reported nowadays.
About a third of those fires are criminal [0], yes that's a lot, but the majority are still accidental or natural.
Even the criminal ones are only enabled because of the dry vegetation, caused by the recent heat waves. IMO focusing on what caused the spark is missing the root cause: global warming.
And yes you can argue that such fires existed previously, but what's concerning is that the frequency on which they are happening is increasing rapidly
In the South of France, dry vegetation in summer is normal. Areas where this is most expected, the Mediterranean, have actually seen a decrease of fires over time as preventive measures and fire-fighting readiness have increased. [1] See graph for "Nombre de feux de foret in zone mediterraneene 1973-2024", graph for "surfaces parcourues", and text.
That's why I am suggesting to keep a cool head and to take a step back to analyse things rationally. In any case that is good advice to adapt to warming, too. If you go down the rabbit hole of media reporting you are going to have a nervous breakdown.
A rational approach to existential threats is indeed good advice, but to surrender in the face of complexity is not.
The human induced climate catastrophe is due to a systemic failure and consequentially needs to be addressed on a systemic level. The economic system and policies need to be adapted, even against the implied subjective interests of the biggest holders of capital and assets.
They like to paint that as "impossible", but of course it's not.
Being trapped in an Overton window selected for you by those invested in upholding the status quo is what leads to your emotional stress.
The fundamental disconnect between the existential threat of climate catastrophe and the official un-reaction to it is what leaves you unable to cope with actually very much white-washed reporting on the topic.
[Answering here to @applepearlime bc limits of my green acct]
They do have firebreaks, paths for trucks to go in many places [1]. I've seen many.
But you could argue they're not wide enough to actually break fire. And when I see videos of how tall and wide the flames are, I have no idea how wide they should be... It's a managed forest though, definitely looked after because economics interests (wood, tourism).
I grew up there. I used to bike along stretches of firebreaks between plots. These firebreaks are nowhere nearly enough. Trees are young, pine needles spread everywhere, and ground is sandy.
The human induced climate catastrophe has reached unprecedented levels because of humanity's continued failure to correctly integrate that reality into their decisions and the resulting inaction.
Landes & Médoc serve as an immediate example of the consequences of that catastrophe being left to unfold unabated.
Using diminutive terms to describe causalities that currently escalate beyond human control and ultimately lead to civilizational collapse with billions of deaths is a dysfunctional disconnect from reality.
You misunderstand. Dibby053 provided interesting context for why specifically that region is so badly affected right now, on a background of global climate catastrophe. Rico98gg is derailing what could have been a more interesting thread with 'no, it's global warming', which is obvious and irrelevant.
It's you that is (intentionally?) missing the forest for the trees (wordplay intentional). The overall pattern of worsening fires is clear and well-documented, and disingenously asking "Why Landes & Medoc specifically?" ignores the broader issue.
Nobody asked that. Information about the local ecology was volunteered, and was much more interesting than yet another argument (being had against nobody) that climate change is a major contributor.
I come from the Mediterranean region and locally we know many explanations for that.
Many of those pine forests are relatively new. Pine trees burn frequently, around every 20-30 years. In the past they used to be mixed with many other original trees, but during the recent century reforestation, pines were planted as the single tree species, making fires more prone to happen and more easily to spread.
In the past, way more population lived next to the forests, where lumber used to be part of their income, so trees were frequently cut, forests maintained and shepherds would bring their sheep to feed from forest lower plants. All of that is gone.
In the past, locals used to be able to build firewalls, clean forests and fight fire with fire (provoking small controlled wildfires to stop the big ones). Green policies forbid those actions nowadays.
Also, if we talk about past centuries, temperatures used to be higher during early middle age and before. These high temperatures are nothing new in terms of historical forest.
Also, looking at the statistics, we’re probably at the bottom number of wildfires per area in the last 70-80 years, while total forest mass has probably increased around 40-50%.
> Also, if we talk about past centuries, temperatures used to be higher during early middle age and before. These high temperatures are nothing new in terms of historical forest.
This was the hottest year on record. 10 of the last 15 years have been the hottest year on record, consecutively. What makes you believe this fake information about the middle ages?
Someone heard about the Medieval Warm Period, looked at the Wikipedia page, saw the temperature data for the Greenland ice sheets and misinterpreted it to mean global temperature. It fits in well with the 'well, the Jurassic was warmer than today and there were no humans then, so you can't be sure that we're responsible for any climate change that may be happening' argument.
None of what you are writing is applicable to Landes. Outside of scandinavia Landes region is some of the most intensely managed forest in Europe.
From planting to cutting is only around 30-50 years. With multiple thinnings in between. Also none of that forest existed 200 years ago and there never was anything other than pine planted there for those 200 years, in the beginning for resin, now for pulp.
And so none of it burned in the middle ages or was affected by any higher temperatures because it didn't exist back then.
It does seem that the area burnt p/year by wildfires hasn't grown in the last 40 years in Europe, and even decreased slightly. This is somewhat odd to me. The evacuation and disruption of settlements seems to have increased in severity in the last few years, or at least the media gives that perception. If I'm looking at the wrong data and this could be misleading, then apologies.
I love how four comments down there is someone posting:
"You’re both right.
However OPs post is more useful than yours.
By now, everyone knows about climate change. But I assume most didn’t know the fact about the pine trees in this area.
Nowadays it’s much more about how we deal with climate change and not so much about the fact that there is human made climate change"
Thank you for proving that there are, in fact, still climate change deniers even here on hacker news.
I'm assuming you're a climate change denier. You don't say so outright, but "Green policies forbid those actions nowadays" is a bit of a dogwhistle that you oppose environmental protection regulations broadly (not merely overzealous ones that have side-effects that make combating certain types of wildfires harder in certain situations), and:
"Also, if we talk about past centuries, temperatures used to be higher during early middle age and before. These high temperatures are nothing new in terms of historical forest.
Also, looking at the statistics, we’re probably at the bottom number of wildfires per area in the last 70-80 years, while total forest mass has probably increased around 40-50%."
Well... that's pretty close to just coming out and saying you don't believe in climate science.
These factual corrections are warranted. But IMO the accusations of dog-whistling and wrongthink are unnecessary and counterproductive. Again: I agree with you on the substance! And this probably is a climate denier. But (1) that's not very interesting in itself, and (2) by adopting an accusatory tone we're just going to push them and their sympathizers into a posture of defensiveness and victimhood which will only worsen the polarization and make the whole problem even harder to solve than it already is. IMO, on this issue it's best just to stick doggedly to factual correction and avoid the temptation to police people's inner minds.
On the one hand I agree with you, on the other hand I think this is highly idealistic:
Most people would have a hard time debating a flat-earther since it's their hobby and they master all the talking points whereas you spent maximum one hour even thinking about it in the last 10 years. They will get you in a dark forest of details you don't know how to navigate and win the argument.
I am so sorry for the one in a million crackpot-sounding genius that will get hurt in the process but social shunning is just so so much more effective. No wonder the crackpots and grifters are back and running the show nowadays
I think a better approach is to ask people who have contrarian/non-consensual opinions to show that they know that they are crackpots out and to distance themselves from them:
"I know some people come up with conspiracy theories that says climate is a hoax designed to control populations because they don't want to change anything in their way of life but that's not what I am. I just care about the science and I think I found a real flaw in the leading explanation of climate change. I'd love for someone with knowledge about to discuss it with me to see if they took X into account" etc.
This above is what I expect but if you quack like a quack, you're probably a quack and you'll get the social shunning treatment
The dark ages and the plague saw a lot of belief in religion and rejection of science that lead to excessive deaths all over europe. Medicine was studied and practiced in the arab world and jewish doctors were the only ones allowed to bring some of those practices to Europe. Religion was preventing tested and verified approaches to treatment. Today Europe needs to stop repeating that practice. Believing in human caused climate change doesn’t stop you from learning proper tested mitigation strategies against wildfires, cooling of people in cities, nuclear energy or anything else that allows you to mitigate the effects of your climate religion. Because you can mitigate death in your area way before you can stop china or any other high emitter from emitting CO2 on the other side of the planet from you and contributing to global warming.
There is no dichotomy between preparing for the inevitable and preventing the preventable.
Painting the actions of people on the other side of the planet as "out of anybody's control" is hubris though. Humanity very well is capable of organizing on that scale and has done so regularly for a long time already.
The actual problem is the disconnect between the interests of those in charge of such organization and the well-being of the public.
Villages all over the world since ancient times would have houses with some form of a summer kitchen. During hot days the temps in the house are already uncomfortable and cooking there would make things worse, so they built basic kitchen facilities away from the main house to keep heat and smoke and smells out (that also reduced some fire risks).
Many western countries now summer-kitchen most of their uncomfortable output to corrupt poorer countries where the leadership doesn’t mind taking cash for poisoning their citizens. The naïveté is then claiming that those poorer countries are then the main polluters. Recyclables in the US and a lot of Europe are shipped off to southeast asia thus 80% of plastics in the ocean are found there. A train of plastic to be burned was even shipped to Bulgaria (a EU member) by the mafia a few years ago.
In the mean time “carbon credit” companies have their offices in Hong Kong and are guilting Disney and Adidas and Apple and any Western public brands into paying for “carbon laundering”. Forests that would have been planted anyway for lumber collect carbon credits as extra income right before selling said lumber for consumption. It takes real faith to keep believing any of the activity actually removes carbon legitimately, but the money movement in that movement is very real.
While anyone can target the source of the warming with any resource they want to dedicate, and should be free to do so. Governments need to focus on mitigating the risks to human life and that involves real fire prevention (trimming, controlled burns - maybe smart tech the smoke so it gets captured instead of irritating the noses of non-summer-kitchen citizens), clean energy generation, and installing damn air conditioning units into old European capitals so Europeans don’t end up dying in droves from preventable basic climate change consequences.
"but "Green policies forbid those actions nowadays" is a bit of a dogwhistle that you oppose environmental protection regulations broadly (not merely overzealous ones that have side-effects that make combating certain types of wildfires harder in certain situations)"
thats a bit of a "dogwhistle" that you're not actually convinced that green policies can ever be deranged and counterproductive. On the contrary. I don't know if you're a a brainwashed virtue signaler, but I'm assuming it. You don't say so outright, but the mental gymnastics of calling someone a climate changer denier who just said climate change is widely recognised are staggering.
This truly is the least intelligent timeline. Please check with Dunning and Kruger if you're part of the problem.
It's not, but the original comment never claimed that it was.
There have been 4 or 5 pretty massive wildfires in France that I can remember in the last 5 years, but this is the first time they've had to deal with pyrocumulonimbus caused by a wildfire. Global warming was likely a contributing factor for all of those fires, but global warming alone doesn't explain why this one is different. The first comment about the pine isn't answering "why is this happening now?", it answers the question, "why is this fire so much worse?"
Decades ago i was a big wall rock climber. We would often see old photos of mountains and cliffs and remark "where are the trees?" Areas we knew to be covered in forrest were bare only a century ago. This wasnt logging (climbing areas are too rugged to be logged bare.) There were just fewer trees. The general assumption was CO2. The combination of longer growing seasons and more plant food (co2) may mean there are simply more trees.
The timing is curious to me. Atmospheric CO2 didn't really start picking up bigtime until 1970, and trees, even fast growing pines, take decades to grow.
I just listened to a podcast last week with the author (Dex Horthy) on as the guest. Humanlayer (his company) is constantly trying to push the limits with agents and he's very into using them.
He's well aware of exactly how good the models are today and I'm sure that if he thought they were good enough now to make the dark factory idea work, they'd be trying again.
Just to offer a different perspective, my last job removed QA and it was a nightmare. Feature delivery slowed way down and incidents and bugs went way up to the point where we started losing customers.
In theory, I agree with what you're saying, but I think a codebase needs to be in a certain state and a company's leadership needs to be in a certain mindset to make it work. Our codebase was far too large and interconnected for any developer to fully understand all of it because of years of building with unclear boundaries between teams. QA's value wasn't really the testing they did. The value was that we had a dedicated team who's job it was to see the big picture and keep up with the changes 15 different teams were making on the same product. Management wanted the benefits of removing QA without the pain of paying down all the organizational and tech debt that made them valuable.
Again, I agree with your sentiment, but also, I think that most large organizations are not willing to do the necessary work to get a place where QA can be removed.
Sounds just like every regular software project. That’s why cutting QA is a bad idea for every regular software project. Same goes for product management, unless you are Google and can afford building products people don’t need.
We’ve never had a QA because we are on a tight budget but our PM is acting as a gatekeeper before declaring something as done.
However, there were too many cases that things were delivered as “ready” when they were not. PR review was not enough as everyone were checking diffs from GitHub only.
I implemented an intermediate step where the responsible engineer must post a screenshot or a short video of the ticket before passing to the PM and that alone resolved a lot of issues before they materialized on customers screens, just because you must take the extra effort to work on a proof of work.
My experience is that what you're suggesting isn't a perfect solution.
reply