Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Schedule tasks on the web

code.claude.com

Post reply on HN
Print view View original

101–110 of 261 posts

Re: Schedule tasks on the web

#101

Post by gf000 »

eksu wrote: post #40
chatmasta wrote: post #19

Earlier quoted context omitted.

I love everything about this direction except for the insane inference costs. I don’t mind the training costs, since models are commoditized as soon as they’re released. Although I do worry that if inference costs drop, the companies training the models will have no incentive to publish their weights because inference revenue is where they recuperate the training cost. Either way… we badly need more innovation in inf…

This is the wrong way to see it. If a technology gets cheaper, people will use more and more and more of it. If inference costs drop, you can throw way more reasoning tokens and a combination of many many agents to increase accuracy or creativity and such.

> throw way more reasoning tokens and a combination of many many agents to increase accuracy or creativity and such.

But this is just not true, otherwise companies that can already afford such high prices would have already outpaced their competitors.

Re: Schedule tasks on the web

#102

Post by raincole »

slopinthebag wrote: post #48
Leptonmaniac wrote: post #30

Earlier quoted context omitted.

I think that as a user I'm so far removed from the actual (human) creation of software that if I think about it, I don't really care either way. Take for example this article on Hacker News: I am reading it in a custom app someone programmed, which pulls articles hosted on Hacker News which themselves are on some server somewhere and everything gets transported across wires according to a specification. For me, this…

Art is and has always been about the creator.

I don't want software that is built to be art. I want software that is built to provide facilities.

Re: Schedule tasks on the web

#103

Post by fhub »

theredbeard wrote: post #52
nickandbro wrote: post #4

I feel like we are just inching closer and closer to a world where rapid iteration of software will be by default. Like for example a trusted user makes feedback -> feedback gets curated into a ticket by an AI agent, then turned into a PR by an Agent, then reviewed by an Agent, before being deployed by an Agent. We are maybe one or two steps from the flywheel being completed. Or maybe we are already there.

We haven’t been inching closer to users writing a half-decent ticket in decades though.

Solutions like https://bugherd.com/ might make the issue context capture part more accurate.

Re: Schedule tasks on the web

#104

Post by TeMPOraL »

ares623 wrote: post #95
jngiam1 wrote: post #22

Earlier quoted context omitted.

MCP tools. We're doing some MCP bundling and giving it here, pretty cool stuff.

wasn't MCP a critical link in the recent litellm attack?

And if it was?

It's a bit like asking if "an API" was a critical link in some cybersec incident. Yes, it probably was, and?

Re: Schedule tasks on the web

#105

Post by girvo »

slopinthebag wrote: post #24
nickandbro wrote: post #4

I feel like we are just inching closer and closer to a world where rapid iteration of software will be by default. Like for example a trusted user makes feedback -> feedback gets curated into a ticket by an AI agent, then turned into a PR by an Agent, then reviewed by an Agent, before being deployed by an Agent. We are maybe one or two steps from the flywheel being completed. Or maybe we are already there.

What kind of software are people building where AI can just one shot tickets? Opus 4.6 and GPT 5.4 regularly fail when dealing with complicated issues for me.

GPT 5.4 straight up just dies with broken API responses sometimes, let alone when it struggles with a even moderately complex task.

I still can't get a good mental model for when these things will work well and when they won't. Really does feel like gambling...

Re: Schedule tasks on the web

#106

Post by ares623 »

TeMPOraL wrote: post #104
ares623 wrote: post #95

Earlier quoted context omitted.

wasn't MCP a critical link in the recent litellm attack?

And if it was? It's a bit like asking if "an API" was a critical link in some cybersec incident. Yes, it probably was, and?

i'd say it's more like intentionally choosing to use naive string interpolation for SQL queries than a trusted library's parameter substitution. Both work.

Re: Schedule tasks on the web

#107

Post by girvo »

gowthamgts12 wrote: post #5

interesting to see feature launches are coming via official website while usage restrictions are coming in with a team member's twitter account - https://x.com/trq212/status/2037254607001559305 . also, someone rightly predicted this rugpull coming in when they announced 2x usage - https://x.com/Pranit/status/2033043924294439147

Funnily, Anthropic's pricing etc. why I'm using GLM-5 a bunch more outside of work. Definitely not Opus level, but surprisingly decent. Though I got lucky and got the Alibaba Coding Model lite plan, which is so cheap they got rid of it

Re: Schedule tasks on the web

#108

Post by TeMPOraL »

ares623 wrote: post #106
TeMPOraL wrote: post #104

Earlier quoted context omitted.

And if it was? It's a bit like asking if "an API" was a critical link in some cybersec incident. Yes, it probably was, and?

i'd say it's more like intentionally choosing to use naive string interpolation for SQL queries than a trusted library's parameter substitution. Both work.

There is no "parameter substitution" equivalent possible. Prompt injection isn't like SQL injection, it has no technical solution (that isn't AGI-complete).

Prompt injection is "social engineering" but applied to LLMs. It's not a bug, it's fundamentally just a facet of its (LLM/human) general nature. Mitigations can be placed, at the cost of generality/utility of the system.

Re: Schedule tasks on the web

#109

Post by pxtail »

mindwok wrote: post #75
nickandbro wrote: post #4

I feel like we are just inching closer and closer to a world where rapid iteration of software will be by default. Like for example a trusted user makes feedback -> feedback gets curated into a ticket by an AI agent, then turned into a PR by an Agent, then reviewed by an Agent, before being deployed by an Agent. We are maybe one or two steps from the flywheel being completed. Or maybe we are already there.

I think Anthropic will launch backend hosting off the back of their Bun acquisition very soon. It makes sense to basically run your entire business out of Claude, and share bespoke apps built by Claude code for whatever your software needs are.

100% its going to happen - also OpenAI will do same, there were already rumors about them building internal "github" which is stepping stone for that Also it is requirement for completing lock-in - the dream for these companies.
Post reply on HN