this is the way.
Replying to @paulg
After many, many years of presuming good faith, I’m finding myself increasingly drawn to a Konmari curation policy: if the prospect of further interaction with a commentator does not spark joy, regardless of whether they are benign intent, block/mute and move on with life.
1
8
6,464
Replying to @wilsonyimby
Related?
teapawt.net/weakinstrument/status/…
Unbelievably funny that the banks had to tell SpaceX “no we will not lend to you if you shoot the collateral of the loan into space.”
1
If you're using an agent harness you should be able to point it at this thread and at recursive-mode.dev (by @trydotworks) and it should be able to figure out my process. Or just copy and paste the first three posts and the two attached images into it.
1
19
It did the review, wrote the improvement plan, chunked the plan, dispatched subagents to do the work, reviewed the work, made corrections, modified the following chunk from what it learnt or postponed features to an even later chunk , rinse and repeat. All on its own for 5+ hours
1
28
Replying to @airkatakana
That must have been quite the experience
teapawt.net/CenturiiC/status/21234…
1
1
73
This is with deepseek-flash as the designated subagent model. Both from their first-party providers respectively.
1
29
Today one of my clanker's weekly self-improvement loops took more than 5 hours. 🥳
(I should have picked the Highspeed option for kimi-3.1-pro 😐)
(This goes to show how little progress I've made / how early I am in using LLMs and agent harnesses)
1
2
104
Replying to @kiwicarrotcake
I think it's quite underwater at the moment, but two tides are beginning to turn: 1) energy costs 2) labour costs (including pension). Turn around in 3 years?
1
14
Replying to @DJLougen
I don't think that's a dumb question, but at the same time, have you tried using `fff` or similar? (I think Hermes Agent and many other harnesses default to ripgrep)
github.com/dmtrKovalenko/fff
96
Replying to @capitalatrisk23
1
27
Two hero* trades going into next week to keep an eye on:
1) Japan Tobacco 2914.T
2) Abivax $ABVX
* This is NOT a good thing
If you aren't an existing shareholder you really should be keeping an eye on Japan Tobacco 2914.T
(with apologies to @CacheThatCheque and other existing shareholders)
4
456
Replying to @atelicinvest
My gut was telling me to do just that before Friday open and I did not listen to my gut 😩
3
88
… or not 😰
teapawt.net/AKL_019/status/2094790…
Replying to @AKL_019
7. Given these trends, Meituan’s long-term future is quite clear. One quarter of up or down is not really going to make much of a difference.
44











