HackerTrans
トップ新着トレンドコメント過去質問紹介求人

eddyzh

214 カルマ登録 3 年前

投稿

Long-running Agents (Summary of the current state on many fronts)

addyosmani.com
2 ポイント·投稿者 eddyzh·2 か月前·1 コメント

The Mythical Agent-Month

wesmckinney.com
4 ポイント·投稿者 eddyzh·5 か月前·0 コメント

コメント

eddyzh
·2 時間前·議論
The fact that is is ai generated.
eddyzh
·29 日前·議論
For that test you have to compare letting a fresh agent (subagent) or the same model do the same review.

The fact that a review helps does not prove the model choice for the review.

You reviewing your own writing helps too!
eddyzh
·2 か月前·議論
Added the () part since this title has been used a lot in other articles.
eddyzh
·3 か月前·議論
Exactly this.

This may be worth the discount. Or not if your time and attention is worth (quite) a lot.
eddyzh
·3 か月前·議論
At work I use opus max Fast It hardy ever fails for no reason even if I forget to give it all the right context. At home i run sonnet, and it does not get what I meant or expected 20-35% of the time. Due to the enormous difference in cost, depending on the value of your time (hourly rate) that might be a nett benefit.

Sonnet being faster alone would not be worth the failure rate for me.

At home i just not want to pay more than 20 bucks for incidental projects.

And opus max would just consume my tokens in one round.
eddyzh
·3 か月前·議論
Thank you. This is great to hear!
eddyzh
·3 か月前·議論
While chatGPT was not out then, the ML that drives robotics was acting by then very much.
eddyzh
·4 か月前·議論
In had one app like that from Cydia Loved it.
eddyzh
·4 か月前·議論
Original artikel https://open.substack.com/pub/alexeyondata/p/how-i-dropped-o...
eddyzh
·7 か月前·議論
Would that be unified memory? Where the gpu and cpu can share the memory? Which is key for performance.