HackerTrans
TopNewTrendsCommentsPastAskShowJobs

peheje

305 karmajoined 9 years ago

comments

peheje
·2 days ago·discuss
makes sense? commit messages is pre ai era, we need a new git, and people are already working on it
peheje
·11 days ago·discuss
Reminds me of 'Learning to be me' by Greg Egan
peheje
·14 days ago·discuss
Reason people want the best: people want to believe their project is so advanced that they need the most clever LLM possible. To say otherwise is to admit that it's not really frontier or novel in any way. And people don't like that.
peheje
·15 days ago·discuss
I completely trust the government to keep dangerous AI away from bad guys. After all, they did a perfect job stopping illegal guns and drugs.
peheje
·15 days ago·discuss
OpenRouter sometimes chooses a very expensive provider. Try the floor slug or choose directly the provider. I moved to just putting 5 dollars directly on deepseek instead of going through OR.
peheje
·last month·discuss
resistance is futile
peheje
·last month·discuss
there will be a lot of paper clips
peheje
·2 months ago·discuss
I mean indsight is 20/20, but saying that is like saying "everyone will just use the best tools". That's not what we see most places in the world for most types of resources.
peheje
·2 months ago·discuss
We try to keep things simple. Everything has risks. No stall, run async, backward compatible. DB handles rollback via transactions. Happy to expand if interested.
peheje
·2 months ago·discuss
Deploying SQL changes? Why not just let the application do that on startup. Ofcourse be backward and forward compatible. SQL change only deploy.

"Update something in the cloud" <- What do you mean?
peheje
·2 months ago·discuss
first impression: the tui flickers a lot, unpleasent. very laggy to write in.
peheje
·2 months ago·discuss
having issues with truncated output from deepseek v4 pro through openrouter via pi-harness on ptyxis-terminal using ubuntu

trying reasonix with direct api..
peheje
·2 months ago·discuss
Agreed. And the gained time either goes toward 1) more experiments, or 2) leisure, which makes you sharper in the lab and happier overall. Not sure the "I saved $17,000 so far" framing is the most useful way to look at it, but it's a cool project and I love that people are doing this kind of thing.
peheje
·2 months ago·discuss
[flagged]
peheje
·2 months ago·discuss
The future will have LLMs running local at your laptop/devices. If not almost exclusively then at least for 90-95% of the tasks. Speculative decoding is just one technique out of many existing and more to come that will make this even more viable. The gap is closing on both fronts. Software gets faster/more clever. Hardware gets faster and smaller. The single user story is the story. I'm obviously speculating myself, but that's how I see it.
peheje
·2 months ago·discuss
Maybe the end state of computing is not humans learning how to speak to computers, but computers learning how to speak to humans.

Think the movie Her 2013. OS1 it's called.
peheje
·2 months ago·discuss
[flagged]
peheje
·2 months ago·discuss
https://sinceyouarrived.world/taken
peheje
·3 months ago·discuss
what about just personal stuff in a syncing interface, what do you use for that?
peheje
·3 months ago·discuss
Manage the budget not the impl. Top down decisions like "use a cheap model" risk optimize for the wrong things. If we lose 90% cache hit on the expensive models to context switch to a cheap one, there's no savings. Set the budget, let the devs optimize.