IMO Django is a buggy and poorly designed framework that locks you into bad decisions.
It's a combination of things that all suck: the
- ORM (sqlalchemy is better in every possible way. django's orm is very poor and can't express a lot of sql constructs at all)
- templates (jinja2 is basically identical except performant and debuggable)
- routing (lots of wsgi routers exist and are lightyears ahead of django)
It's not that you need to ask it to be honest, it's that the defaults are kind of stupid and obnoxiously sycophantic. ChatGPT is also prone to getting stuck on particular ideas. If you're using the vanilla personalities without a custom prompt, not aware of and working against its issues, and not starting new chats occasionally you won't get good results. You'll get good-sounding garbage.
Part of my custom prompt is
```When using factual information beyond what I provide, verify it when possible.
When researching factual questions—especially by relying on papers and studies—actively look for null findings, negative results, and contradictory evidence, not just positive or confirmatory findings.```
To me, the most interesting result of that part of my prompt is that in thinking mode, it ends up re-checking it's assumptions and sources fairly often. It's not about honesty, but correctness.
A custom prompt isn't the be-all end-all either. The right kind of questioning is important, and you also need to get a fresh context when you ask new questions or if you want to double check something.
It's interesting because presumably you were too ashamed to tell the doctor "we pasted stuff into chatgpt and it said it means she is sick", because if you had said that he would have looked at the bloodwork and you could have avoided going to a specialist.
It's an interesting cognitive dissonance that you both trusted it enough to go to a specialist but not enough to admit using it.
We don't have a marketing department, so we're happy to take suggestions on our messaging!
What makes it modern are the ideas behind it: the column-oriented layout, support for lightweight encodings such as FSST and FastPFOR and support for pre-tessellation. Also, enabling doing more computations on the GPU instead of the CPU, which are made possible thanks to modern graphics APIs like Vulkan and Metal. I agree that it is better to be specific about these things (if that is your gripe with it), but there's only so many characters that fit into a title. ;)
Codex is extremely bad to the point it is almost useless.
Claude Code is very effective. Opus is a solid model and claude very reliably solves problems and is generally efficient and doesn't get stuck in weird loops or go off in insane tangents too often. You can be very very efficient with claude code.
Gemini-cli is quite good. If you set `--model gemini-3-pro-preview` it is quite usable, but the flash model is absolute trash. Overall gemini-3-pro-preview is 'smarter' than opus, but the tooling here is not as good as claude code so it tends to get stuck in loops, or think for 5 minutes, or do weird extreme stuff. When Gemini is on point it is very very good, but it is inconsistent and likely to mess up so much that it's not as productive to use as claude.
Codex is trash. It is slow, tends to fail to solve problems, gets stuck in weird places, and sometimes has to puzzle on something simple for 15 minutes. The codex models are poor, and forcing the 5.2 model is expensive, and even then the tooling is incredibly bad and tends to just fail a lot. I check in to see if codex is any good from time to time and every time it is laughably bad compared to the other two.
I have the complete opposite experience. Claude Code is for building small demo apps. Like a 10 line Javascript example. Codex is for building GPU pipelines and emulators.
Misleading title, they didn't make the packaging library 3x faster, they made reading one attribute of a package 3x faster. The whole library is still very, very slow compared to alternatives.
This reminds me of the time I went to a church dinner with my father.
Everything was fine, but then each person was asked to stand and briefly mention something they were thankful for. About half way through one of the oldsters mentioned their health problems - "I'm thankful they aren't worse" - sigh. Every person after that had to list every health problem they had, and every health problem everyone in their family had. It took like an hour and we were waiting to eat.
I'm not sure what we should do, it's very hard to determine what minimizes harm and maximizes benefits at a global scale. It's certainly not as simple as extremists would like to believe. Certainly it would be much (MUCH) less risky to slow warming as much as possible and maintain constant or slowly reducing CO2 levels.
I think from the standpoint of predicting what will happen, my best guess is that people will use fossil fuels until it is economically not viable to do so. If you want hasten it at an individual level, buy solar panels and have your house disconnected from the grid until fees you pay no longer subsidize fossil fuels. Frown at people and refuse to give them positive social cues when they buy a car that isn't electric. Instead of "oh nice car" just say "it would be so cool if they had a plugin version!". Support electrification of things like heat and water heating so long as it can be powered by non-fossil sources.
In the long run I think solar power, effective battery technology, and the peaking of the global population combine to cause fossil fuel usage to reduce over the next 100 years or so until CO2 levels stabilize. Lots of large CO2 emitters are already leveling off - the output is too high to sustain but at least it's no longer increasing year over year - such as from cement production.
Honestly it's not much but that's what you can do, larger social movements and political action do not work when someone's decision is whether to spend $800 a month or $100 a month to heat their house. Anyone who says it does should buy a thermometer, but instead they will get a plane ticket to the next big city to run around in the street yelling at police (literally the only people paid to not care about your slogans) while nobody really notices.
Electric cars are the savior of the auto industry, not of the climate. It needs to become viable for most people to get around without cars at all. The intensity of their resource consumption, both for manufacture and for infrastructure, independent of their fuel source, cannot scale up for the world population.
If we are in overshoot scenario even reducing emissions may not be enough. There are warming gases currently trapped in permafrost, the natural carbon storage capacity is very dynamic, so global warming may target new (worse) equilibrium beyond what we think we can achieve in best case scenario.
And if my grandmother is dead it's too late to ask her to borrow money. It's easy to chain together low probability what-ifs and come up with everything on fire.
Were you aware that the last time the planet was estimated to have co2 levels over 420ppm the global temperature was 10 degrees Celsius warmer overall? This is the global equilvant of being locked in a car in a sunlit parking lot.
Everyone thinks they are special right? Thinking you are special suggests you likely aren't that special (not saying this about you personally, but still).
Guys, these are a dime a dozen and you never hear about them again.
All like 6 stories from this site on hn are some cancer cure that went nowhere.
reply