HackerTrans
トップ新着トレンドコメント過去質問紹介求人

imhoguy

2,827 カルマ登録 10 年前
[email protected]

投稿

AzoBiPy – stable organic redox flow battery compound

nouvelles.umontreal.ca
1 ポイント·投稿者 imhoguy·5 か月前·1 コメント

コメント

imhoguy
·9 時間前·議論
Now imagine blood pump during surgery.
imhoguy
·9 時間前·議論
I test workloads with multiple closed and at least one open model now. Good to have a backup on 503s or credits run out.
imhoguy
·9 時間前·議論
This is how development looks like for many years now, constant rewrite on the horizon. I think LLM development hype surpassed Blockchain and JS frameworks craze of decade ago.
imhoguy
·18 時間前·議論
CLAUDE.md (or AGENTS.md) is not good place to put all code change rules, because these rules would dillute the context and "distract" the agent e.g. during bugs triage or business analysis.

Instead modularize the knowledge with skills and specialized MD files. Agent should lazy load what is needed to do focused work.

Skills have usage description metadata, but with free files you can simply instruct agent with CLAUDE.md to load them, e.g.: "Before you attempt to change any frontend code first load and follow `docs/{JS|HTML|CSS}_coding_rules.md`".
imhoguy
·23 時間前·議論
No way! It is a while since I have seen that extension here on HN, I couldn't be mistaken. With AI? Is Pascal still alive?
imhoguy
·昨日·議論
Except Amazon (Linux, Elastic, RDS..)
imhoguy
·一昨日·議論
Hopefuly I see conscious young people in my surroundings who refrain from using human like AI (voice). They say "it is cringe".

Moreover I think aggresive robocalls and advertising will derail the entire trend in a few years, people will become tired of fake talk.
imhoguy
·一昨日·議論
The worst is that every agent session is generating so many "btw fix this" side-quests that it is really hard to stay in the task focus. I throw some into todo list manually but still it is exploding by the day. Perfect is enemy of good.
imhoguy
·一昨日·議論
In my place I see currently a governance panel effort mandating around LLM agent skills usage, it is so much shit show that I expect productivity is going to fall to 0.5x pre-agents. But not pre-LLM as autocompletion was really helpful in the trenches. The tool in wrong governing hands and you get sand into cogs thrown.
imhoguy
·一昨日·議論
Isn't it how these fulfilment centers already work that way with all these work manuals. Read AMAZON.md /s
imhoguy
·一昨日·議論
I bet drone van is the next thing to be automated.
imhoguy
·4 日前·議論
Literaly they silently refuse to open the pod doors for you.
imhoguy
·5 日前·議論
... and that actually shows - senior engineers have spent actual paid time to train juniors. Plus they used to spent time contributing to open source projects or Stack Overflow, all the stuff which every company benefits from.
imhoguy
·5 日前·議論
It is like with drug dealers, you get some free dose, then cheap one, then you pay an arm and a leg.

Somebody has to finaly pay for these heaps of accelerator hardware.
imhoguy
·5 日前·議論
oh no! what about all these demos which product management vibe coded?
imhoguy
·6 日前·議論
You need to create review skill and there define what "issue" or "good" are for you to limit sensitiviness. Otherwise you depend on model's random threshold or non of such then you get perfection chasing.

Anyway it will never match your judgemend completely unless you upload your brain dump into model.
imhoguy
·11 日前·議論
Turn off computers and phones. No need for DCs then.
imhoguy
·11 日前·議論
Enshitification. Too big to.. upset the govt.
imhoguy
·12 日前·議論
These parents will do age check themselves on kids devices. Why? To not be bothered or to elevate the kid in peer group.

No system is going to fix "unresponsble" parents until we end up with a state completely replacing parent like in Brave New World.
imhoguy
·16 日前·議論
I still amazed how so many people don't get this entire planet is one feedback loop system of competing life processes and they think hiding in their dusty houses with artificial cures will keep them away from competition and immune against death.