HackerTrans
TopNewTrendsCommentsPastAskShowJobs

eddyzh

no profile record

Submissions

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

addyosmani.com
2 points·by eddyzh·há 2 meses·1 comments

The Mythical Agent-Month

wesmckinney.com
4 points·by eddyzh·há 5 meses·0 comments

comments

eddyzh
·há 29 dias·discuss
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
·há 2 meses·discuss
Added the () part since this title has been used a lot in other articles.
eddyzh
·há 2 meses·discuss
Exactly this.

This may be worth the discount. Or not if your time and attention is worth (quite) a lot.
eddyzh
·há 3 meses·discuss
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
·há 3 meses·discuss
Thank you. This is great to hear!
eddyzh
·há 3 meses·discuss
While chatGPT was not out then, the ML that drives robotics was acting by then very much.
eddyzh
·há 4 meses·discuss
In had one app like that from Cydia Loved it.
eddyzh
·há 4 meses·discuss
Original artikel https://open.substack.com/pub/alexeyondata/p/how-i-dropped-o...
eddyzh
·há 7 meses·discuss
Would that be unified memory? Where the gpu and cpu can share the memory? Which is key for performance.