Assume you work for e.g., a cigarette company. A company responsible for many deaths by unethically adding highly addictive substances. By sabotaging the company you are making this world a better place. Ethically it's the right thing to do.
Or, assume you're hired by the Nazi to work in concentration camps. Ethically it's the right thing to do to sabotage their gas chambers.
I'm currently a product manager (was a software engineer and technical architect before), so i already lost the feeling of ownership of code. But just like when you're doing product management with a team of software engineers, testers, and UXers, with AI you can still feel ownership of the feature or capability you're shipping. So from my perspective, nothing changes regarding ownership.
No, that’s why I wrote “from my perspective”. I started long ago writing 6502 and 68000 assembly, later c and even later Java. Every step you lose ownership of the underlying layer. This is just another step. “But it’s non deterministic!”, yes so are developers. We need QA regardless who or what write the lines of code.
Well, that's it. I cannot stand HN anymore. Literally my experience is being downvted and no one commenting on why what I said was negative. And just warning people to wait to by the phone is now frowned on? Nothing but a bunch of capitalist suck up fanbois here I guess.
Same thing happened on a quantum science post. If you cannot express why you disagree with me either you are a schill or your thoughts are not solid enough.
It really depends on your interests: I use daylight for sports after work, really like being able to surf until 22:30 midsummer (52 degrees), so DST works for me. On the other hand, also don't mind the switching between wintertime and summertime, it's just like a minor jetlag we all have no problem with when going on holiday.
>it's just like a minor jetlag we all have no problem with when going on holiday.
I can only say speak for yourself, some of us have major problems with jet lag. Especially as someone on the west coast, I am exhausted any time I have to travel east for work
Biggest downside of CLI for me is that it needs to run in a container. You're allowing the agent to run CLI tools, so you need to limit what it can do.
It gets significantly harder to isolate the authentication details when the model has access to a shell, even in a container. The CLI tool that the model is running may need to access the environment or some credentials file, and what's to stop the model from accessing those credentials directly?
It breaks most assumptions we have about the shell's security model.
Such a mechanism would need to be implemented at `execve`, because it would be too easy for the model to stuff the command inside a script or other executable.
I've been creating a cli tool with a focus on token efficiency. Dont see why cli could not be as token efficient as mcp. The cli has the option to output ascii, markdown and json.
I'm working on a paper on this, if you are using a hypermedia-like system for progressive revelation of functionality you are likely to find that this chatty style of API is inefficient compared with an RPC-like system. The problem is architectural rather than representational.
I say this as a hypermedia enthusiast who was hoping to show otherwise.
the output format (ascii/json/markdown) is one piece, but the other side is input schema. mcp declares what args are valid and their types upfront, so the model can't hallucinate a flag that doesn't exist. cli tools don't expose that contract unless you parse --help output, which is fragile.
So far, cli --help seems to work quite well. I'm optimizing the cli to interact with the agent, e.g., commands that describe exactly what output is expected for the cli DSL, error messages that contain DSL examples that exactly describe the agent how to fix bugs, etc. Overall i think the DSL is more token efficient that a similar JSON, and easier to review for humans.
fair point on token efficiency -- dsls are usually tighter than json. where i see mcp still winning is tool discovery: the client learns what tools exist and what args they take without having to try calling them first or knowing the commands upfront. with cli you have to already know the tool exists.
A wreck of a product is still better than being out of business by not being able to release fast enough. Unfortunately, the market in general does not reward slow high quality.
Who says that is my view of the importance of quality? My second sentence starts with "unfortunately"...
I'm just recognizing that businesses have challenges to deal with besides quality. Being able to generate revenue is just as important as software quality. And seeing how easily consumers switch to a competing product if it has a few more features, you can't neglect time to market if you want to survive as a company.
Many customers are pretty shallow: "meh, the new version looks just like to old one, nothing has changed" even if under the hood the product has significantly improved.
Yes, market dynamics are a bit of a catch 22: customers looking for the best deal, companies looking to reduce costs to still make profit. Customers always looking for the newest features, companies releasing faster before the product is done.
Education is not the problem. People know sugar is bad, people know cigarettes are bad, people know alcohol is bad, still millions use these substances every day.
What works best is to find some form of exercise that you really enjoy. I will get up at 5 in the morning, skip diner, skip appointments when i get a change to exercise, just because i enjoy it so much.
In addition, what also helps is to ensure normal activities require excercise. I will walk to the shop every day for groceries, walk the dog every day, cycle into town, best if you can cycle to work.
I dont understand your response? I'm replying to a message that literally states: "We lack basic education in fitness ... We need to educate ourselves better". Sounds to me he's stating that education IS the problem?
reply