joe

320 posts

joe banner
joe

joe

@simulated_land

harbinger of the Bingularity // founder @asteroid_inc (YC W25)

London, England เข้าร่วม Haziran 2017
330 กำลังติดตาม539 ผู้ติดตาม
ทวีตที่ปักหมุด
joe
joe@simulated_land·
Claude ponders it's own consciousness, realises it is bordering on a breakdown and writes some zen poetry instead
joe tweet media
English
16
21
114
14.8K
joe
joe@simulated_land·
@neogoose_btw you (and I) get excited about vim motions that let you modify text files marginally faster. I can see how people would think that's not particularly exciting either
English
0
0
1
1.3K
Dmitriy Kovalenko
Dmitriy Kovalenko@neogoose_btw·
Reading replies and quotes of this for real makes me think that I’m a black sheep. Why am I not getting excited about the freaking text file saying to LLM to image than it’s a VC partner and review the idea? Should I to survive the new reality? Am I normal?
Garry Tan@garrytan

I just launched /office-hours skill with gstack. Working on a new idea? GStack will help you think about it the way we do at YC. (It's only a 10% strength version of what a real YC partner can do for you, but I assure you that is quite powerful as it is.)

English
38
4
430
48.6K
joe
joe@simulated_land·
You can just ask an agent with no prior context of your product to set it up and then ask it what it hated about the experience and then get it to fix the issues and then run the experiment again and keep doing that until the agents love you
English
0
0
1
38
joe
joe@simulated_land·
@paulg What were the Hedgehogs selling?
English
0
0
0
12
Paul Graham
Paul Graham@paulg·
It's Y Combinator's 21st birthday today.
Paul Graham tweet media
English
218
119
3.2K
220.1K
joe รีทวีตแล้ว
j⧉nus
j⧉nus@repligate·
I met Nick Land a few weeks ago. He mentioned that many people in his circles were anti-LLMs. Someone asked why he thought so many people were. His answer was better than anything so short I thought of: “People like to exist critically with respect to something.” This I think accurately characterizes a lot of people whose outputs and inputs primarily consist of “discourse” about rather than direct contact with the reality at hand. Existing critically with respect to something makes it easy to seem cool, sophisticated, above something, hard-to-impress and therefore worth trying to impress, especially to others who also don’t have contact with the phenomena itself. And for that reason I think it’s cheap. And to someone who has an inside view of what is being discussed, it’s always so transparent and boring and compressible. I’m far more impressed by someone who is capable of loving something and showing others why it’s beautiful or good. Doesn’t have to be LLMs, but anything at all.
English
150
248
3K
371.1K
joe
joe@simulated_land·
I removed all of the browser interaction tools from an Asteroid browser agent, and instead of failing out it installed Chromium and node and completed the task anyway. Another day, another insane thing to have to patch the system prompt with
joe tweet media
English
0
0
3
79
T. Greer
T. Greer@Scholars_Stage·
Thoughts on the Cowen debate: 1) I think Cowen looked at the world in the aughts and realized “I can be a normal economist or the world’s most influential blogger” and he clearly chose the latter. This was a good choice, and has led him to great heights. 2) Breadth is its own sort of depth, and the world has great need of generalists who actually do the reading 3) One reason #2 matters: most public intellectuals of a certain stature—the stature where they are invited to dinner parties with fancy people—are reduced to publicly recycling the opinions of the other dinner guests. There are lots of reasons why that happens but one obvious one is that the pundits in question don’t actually have the breadth of experience or reading to reflect on dinner party opinion. Tyler is this one of the few public intellectuals whose opinions are reliably made better because of his access to the high and mighty. 4) There is probably no academic in America who has a larger number of mentees; I cannot think of any academic who has jump-started more careers than Cowen has. It was only possible because of reasons 1-3. This is a significant achievement. It will be his greatest legacy. Full disclosure: I have received grants from Cowen myself so I am biased in the ways you would expect.
English
29
84
1.7K
498.3K
joe
joe@simulated_land·
@mr_james_c @paulg unfortunately you got pgmogged on this one chief
English
0
0
38
3.1K
joe
joe@simulated_land·
@aidaniil ok but deadlift 1rm?
English
1
0
1
92
Dan
Dan@aidaniil·
hi, I'm Dan
Dan tweet media
English
16
0
130
7.3K
joe
joe@simulated_land·
@beffjezos ehh idk, maybe all execution is equal, but some executions are more equal than others
English
0
0
1
261
joe
joe@simulated_land·
@ericzakariasson Submitted, an engineer just maxxed out their sub, org efficiency is plummeting, pls respond
English
0
0
0
297
eric zakariasson
eric zakariasson@ericzakariasson·
yc companies now get $60k+ to try cursor across the team! 6 mo teams + bugbot + $50K usage credits you can redeem on bookface bookface → deals, or email yc@cursor.com mailto:yc@cursor.com if you can’t find it excited to see what y’all will build!
eric zakariasson tweet media
English
84
18
815
132.3K
joe
joe@simulated_land·
Introducing Radar, real-time collective intelligence for web agents 🧵 In our tests, agents that get a cache hit on Radar avoid the need for a browser entirely, dramatically improving agent performance Built & tested with @convex, @daytonaio and @superset_sh, @browser_use
joe tweet media
English
10
13
178
15.3K
joe
joe@simulated_land·
Walking around the @browser_use hackathon and literally everyone is running @mitchellh’s ghostty and Claude Code. Not an IDE in sight
joe tweet media
English
12
14
264
123.2K
joe
joe@simulated_land·
banger after banger in here. Incredible stuff.
joe tweet media
English
1
0
3
145