toddmorrow
toddmorrow on Hacker News
Another example
I was simply unable to function with Continue in agent mode. I had to switch to chat mode. even tho I told it no changes without my explicit go ahead, it ignored me.
it's actually kind of flabbergasting that the creators of that tool set all the defaults to a situation where your code would get mangled pretty quickly
I get 10% veteran disability for it. the best time to file a claim is now because they'll change the rules soon and eliminate this benefit
yep. but I don't know what folder. maybe under logs. it's really a new category
his dilemma wasn't moral. he has none. it was a marketing snafu. he marketed anthropic as different when the cost of claiming that was zero. now there's a cost, and he immediately changes his tune. his statement was essentially "why refrain from building killing machines when no one else is refraining? why limit ourselves unilaterally?" duley proves he never had morals in the first place.
you're suffering from Stockholm syndrome
If I wanted a pcb before tariffs, China + shipping << USA + domestic shipping
- I bet that holds true after tariffs. (it does, actually):
PCB Cost: $5.00
Shipping:$5.63
Total:$10.63
- I bet that holds true for custom aluminum parts, etc
for some strange reason, shipping and prices from China << shipping within the USA, still, even after tariffs
"Maker nation" might have been 3D printer company hype. Or just the whole US supply chain is full of price gouging
I was very disappointed to see the little 8% solar. I see that methane isn't budging. if a legacy industry is politically powerful enough, they can absolutely maintain a backwards situation.
city wide municipal Internet service, which is admittedly last mile service, was so cheap it didn't even make a dent in the local tax rates. the cost was nominal. naturally the centralized providers fought to make municipal Internet illegal
a lot of chat websites have a no registration mode so people can try it out
AGI = Reasoning
I can reason. Sometimes. It's very hard. My buddy Deepseek can't. This is like the scene in Blue's Clues where the answer is obvious and the kids are yelling but blue can't see it. Facts abound, but not conclusions based on those facts
There's a reachable intermediate step on the way before reasoning, and that's "keeping the plot". Not losing the line of thought.
so open claw will be neither open nor claw
this is like the doomsday clock
84% is meaningless if these things can't reason
getting closer and closer to 100%, but still can't function
right, the ethereum gets spent whether the transaction is cancelled or not. and that's an issue
there are many many examples where paying a nominal fee seems like it would get rid of the clowns. and it would. almost any place where the public can "post". but the challenge is to not inadvertently throw out the good ones.
once notable policy SQL Server enterprise support used to have was you must be available 24/7 if you submit a critical issue. Microsoft was demanding as much of their time as our time.
not sure how that could be rolled out to repos but it worked
this is just marketing press from big AI
LLMs are like a jack hammer. very good if you hold it and point it. you cannot let go of it for more than half a second. it can hammer but it cannot guide itself.
LLMs have irritated me with bad solutions but they've never hurt my feelings. I can't say that about a single person I know. They're better people than people lol
Facebook is what killed that. Not AI
i have preemptively switched to Deepseek. they'll never remove the free tier because that's how they stick it to Scam Altman and the like
I have an llm riding shotgun and I still very much program by hand. it's not one extreme or the other. whatever I copy from the llm has to be redone line by line anyways. I understand all of my code because I touch every line of it
[using an lmm as stack overflow]
even if you check and redo after paste, you need to check for gotchas. I wish I had a nickel for every time the llm gave me a solution with a hidden limitation. assume that it violates all your unspoken assumptions, and adheres only to what you nailed down in your prompt
for a group of people as smart as developers, it sure took us long enough to realize billionaires were liquidating our code integrity to become trillionaires
Google Maps completely and utterly obliterated my ability to navigate. I no longer actively navigated. I passively navigated.
This is no different. And I'm not talking about vibe coding. I just mean having an llm browser window open.
When you're losing your abilities, it's easy to think you're getting smarter. You feel pretty smart when you're pasting that code
But you'll know when you start asking "do me that thingy again". You'll know from your own prompts. You'll know when you look at older code you wrote with fear and awe. That "coding" has shifted from an activity like weaving cloth to one more like watching YouTube.
Active coding vs passive coding
I'm using a modified version of open Dev. it's just a chat interface for open router. I load a combo box of all the free models. it's fast and it's on a tab where it can't hurt my code
I've you're earning good money and you're young, DON'T QUIT
they don't have reasoning yet
numerous attempts are being made by edge researchers to fix it but their just throwing stuff at the wall
I expect gradual reasoning improvements... not agi to pop out of a box and surprise everyone
and... CEO means "liar"