HackerLangs
TopNewTrendsCommentsPastAskShowJobs

anuramat

148 karmajoined 3 ปีที่แล้ว

Submissions

MiniMax M2 Coding Plan

platform.minimaxi.com
1 points·by anuramat·8 เดือนที่ผ่านมา·0 comments

comments

anuramat
·1 ชั่วโมงที่ผ่านมา·discuss
so, git?
anuramat
·1 ชั่วโมงที่ผ่านมา·discuss
> it's not actually a financially efficient way ... unless you profit from creating demand for LLMs

well, they do? it's a win-win, you can't really criticise an AI lab for doing AI instead of straight up giving money to security researchers

> If you factor in all the money spent on training

why would I? it's not a cybersec-specific model
anuramat
·2 ชั่วโมงที่ผ่านมา·discuss
I imagine one could one-shot a basic app and then feed feature requests one by one, sounds like an obvious way to benchmark architecture/maintainability
anuramat
·3 ชั่วโมงที่ผ่านมา·discuss
> data centers being built in their communities

> golf courses are a traditional green space where people in a community

I have a feeling those two sets of communities are disjoint
anuramat
·3 ชั่วโมงที่ผ่านมา·discuss
if you don't make your own tech, standards will be defined by people that do
anuramat
·10 ชั่วโมงที่ผ่านมา·discuss
whats the point of a commit message if it can be inferred by an agent from the diff?
anuramat
·เมื่อวานซืน·discuss
why?
anuramat
·เมื่อวานซืน·discuss
the article implies that the perfect balance is 1:1; I want to believe this is just some sort of a ragebait-based PR strategy
anuramat
·เมื่อวานซืน·discuss
> they are ... finding ... vulnerabilities ... that have not been worth the time and effort ...

that's kinda the entire point
anuramat
·6 วันที่ผ่านมา·discuss
> 80-90% of the results

why would I ever want 80% of the results though?
anuramat
·6 วันที่ผ่านมา·discuss
research, refactoring, architecture

also just code-that-is-not-as-shit in general

for clearly defined stuff smaller models are fine, but at that point I'd rather write the code myself

in any case, if there's a chance a cheaper model will fuck it up, is the price diff worth gambling with your time?
anuramat
·6 วันที่ผ่านมา·discuss
> this year or next

maybe; I meant "in a single year eventually", not this year necessarily

> what research

transformers were published in 2017, and nobody anticipated agentic coding back then; but if I had to guess:

1. lean self play as in https://arxiv.org/abs/2502.00212 and https://arxiv.org/abs/2606.13473

2. "recursive self improvement"/autoresearch

even basic stuff like coding agents removes a major bottleneck -- when finding relevant literature and turning an idea into code takes as much time as writing it down in your notes, researchers from top tier labs can test every single hypothesis they can come up with

> hilarious

"oneshot a PoC -> oneshot a production ready game" improvement sounds like something that will eventually be done in a 1kloc diff in the RL pipeline

IMHO: "genuinely good" might never happen though because of all the non-coding stuff -- you can't really benchmaxx when the target is defined as "pleasant to humans"
anuramat
·7 วันที่ผ่านมา·discuss
> 100000x in a year

why not? fable 5 (2026) is an inf% improvement over having nothing (2022)

in any case, stop pretending that it can be represented by a single scalar value, or at least use log scale units
anuramat
·7 วันที่ผ่านมา·discuss
> think about what my next question might be

or you could just say it yourself instead
anuramat
·7 วันที่ผ่านมา·discuss
how is GPT more general than LLM? also it's not really "LLM vs RL", they're kinda orthogonal
anuramat
·8 วันที่ผ่านมา·discuss
> 80-90% efficiency

wdym by that

> for daily tasks

which are?
anuramat
·10 วันที่ผ่านมา·discuss
> much more difficult

as in time consuming or error prone?

if it's just time consuming, it still might be faster than writing it yourself
anuramat
·10 วันที่ผ่านมา·discuss
> how would the patient see it

idk, I just know doctors who complained about the same thing for years
anuramat
·11 วันที่ผ่านมา·discuss
he isn't wrong about the doctors though
anuramat
·11 วันที่ผ่านมา·discuss
if you can't tell if slop is correct, how do you know your code is correct? starting with a mental model and then writing the code yourself surely makes it feel safer, but it doesn't mean it is

besides, it doesn't even have to be about writing code; finding a bug is more time consuming than fixing it, so you could at least limit yourself to that