Pav

2.5K posts

Pav banner
Pav

Pav

@pav_light

channelling chaos into whimsy. M-F it's channelled into enterprise tech. multi-media dabbling, cyborg ritual tech at https://t.co/bV4rvCkSmG

เข้าร่วม Eylül 2021
1.4K กำลังติดตาม762 ผู้ติดตาม
ทวีตที่ปักหมุด
Pav
Pav@pav_light·
I just articulated what I care about in 1 kewl sentence during a coffee chat: Scaling transformative educational experiences that help people meaningfully acclimate to AI and technology
English
5
0
20
1.5K
Pav
Pav@pav_light·
I'm pondering the difference between the genres of fantasy and science fiction. Paraphrasing a definition I read from V Rao, fantasy is about exceptional people and science fiction is about exceptional rules. This is especially on my mind now after watching what felt like a quite subpar sci-fi movie. Sci-fi goes wrong when it, 1) veers too heavily into great man 2) when the future is depicted basically like the present plus whatever their pet thing is. Like in this movie, it shows New York City, except w flying cars and slightly more OP guns, but people are living in like ugly & tiny apartments that look like jail cells and yet somehow it is like economically reasonable for like flying food carts to appear at their window / to have motorized furniture
English
1
0
1
34
Pav
Pav@pav_light·
so so under-discussed in popular culture how psychoactive it must be to be an actor in a film or a play. like, these people are literally embodying different people all out, loving different partners, having different tics or neuroses. so wild???
English
2
0
7
111
Pav
Pav@pav_light·
Yeah, interesting design problem, and I've noticed that this feels like a bottleneck to me. Currently trying to structure things loosely according to PARA. I'm letting my LLM system determine salience based on my stated goals, but love the idea of creating something more visual with that data.
English
0
0
0
49
melody kim
melody kim@melodyskim·
personal wiki is a good idea — generally have been feeling this need to capture + visualize the whole universe of data and artifacts i’m using and generating with AI… getting lost in all the folders and files. open to other mental models
Farza 🇵🇰🇺🇸@FarzaTV

This is Farzapedia. I had an LLM take 2,500 entries from my diary, Apple Notes, and some iMessage convos to create a personal Wikipedia for me. It made 400 detailed articles for my friends, my startups, research areas, and even my favorite animes and their impact on me complete with backlinks. But, this Wiki was not built for me! I built it for my agent! The structure of the wiki files and how it's all backlinked is very easily crawlable by any agent + makes it a truly useful knowledge base. I can spin up Claude Code on the wiki and starting at index.md (a catalog of all my articles) the agent does a really good job at drilling into the specific pages on my wiki it needs context on when I have a query. For example, when trying to cook up a new landing page I may ask: "I'm trying to design this landing page for a new idea I have. Please look into the images and films that inspired me recently and give me ideas for new copy and aesthetics". In my diary I kept track of everything from: learnings, people, inspo, interesting links, images. So the agent reads my wiki and pulls up my "Philosophy" articles from notes on a Studio Ghibli documentary, "Competitor" articles with YC companies whose landing pages I screenshotted, and pics of 1970s Beatles merch I saved years ago. And it delivers a great answer. I built a similar system to this a year ago with RAG but it was ass. A knowledge base that lets an agent find what it needs via a file system it actually understands just works better. The most magical thing now is as I add new things to my wiki (articles, images of inspo, meeting notes) the system will likely update 2-3 different articles where it feels that context belongs, or, just creates a new article. It's like this super genius librarian for your brain that's always filing stuff for your perfectly and also let's you easily query the knowledge for tasks useful to you (ex. design, product, writing, etc) and it never gets tired. I might spend next week productizing this, if that's of interest to you DM me + tell me your usecase!

English
7
2
34
6.1K
Pav
Pav@pav_light·
@s0ulDirect0r :ooo that is so frickin cool . could you feel the key forming?
English
0
0
1
20
anansi 🌞
anansi 🌞@s0ulDirect0r·
i've been going through some imaginal shit ever since finishing Mathematica. i found the Image i have around my math aspirations, this locked door in my mind, and there was this key slowly forming, and the other day the door opened and now it's this huge sapphire blue portal.
English
2
0
21
487
Pav
Pav@pav_light·
Being able to ask for help is op. Like I'm realizing that I have a hard time even asking an LLM a super underscoped problem. So it's been really good practice getting more honest about exactly where I am, where my confusion is, and how much help I want to ai (and friends, ofc)
English
0
0
4
67
Pav
Pav@pav_light·
@Thomasdelvasto_ yes... I think seeing oneself fully is so big in this quest
English
0
0
2
23
Θωμᾶς del Vasto
Θωμᾶς del Vasto@Thomasdelvasto_·
so I have the problem of wanting to connect with people more I keep trying to solve it by TALKING about it, saying hey I want to connect to ppl more. instead I think it might be better to focus on connecting more to myself first, instead of talking about it
English
5
0
18
353
Liam Rosen
Liam Rosen@Liface·
@pav_light How about starting with a non-anon profile photo? Let the world see your wonderful smiling enthusiastic face!
English
1
0
1
33
Pav
Pav@pav_light·
wait ...
Pav tweet media
English
1
0
4
118
Pav
Pav@pav_light·
@alitaylor I like the distinction of "check in w self" and "God" huh!
English
0
0
0
3
ali
ali@alitaylor·
i started a habit of journaling every day at the start of 2026, and i picked up praying every day for lent, and now i think i'm stuck with both of these habits for life. highly recommend dedicating time daily to check in with yourself and check in with god
English
12
2
109
3.7K
Pav
Pav@pav_light·
@callanable yall.... raycast saves ur clipboard history... changes the game (and the phenomenology)
English
0
0
2
48
Callan
Callan@callanable·
do you feel it in your left hand when you have something copied to your Clipboard?
English
19
2
35
1.7K
Pav
Pav@pav_light·
One thing about ai timelines is that it really changes your tolerance for frou-frou, feel-good delusions, including those of the spiritual variety. gotta be relentlessly filtering out delusions to be left with nothing but 200-proof faith.
English
0
0
1
75
Pav
Pav@pav_light·
@rachelclif know its meant for men but appreciate the safety prompts
English
1
0
1
137
Pav
Pav@pav_light·
@left_pad I was just thinking I'd love to build this for myself today. Would love to join.
English
1
0
0
17
Pav
Pav@pav_light·
interesting. yeah, I noticed today we were stuck in debugging today, Claude just decided to give up at a certain point and make a hacky shell script, even though I was ready to keep going. maybe I need to be giving Claude more resilience being positive + activating its joy vectors
Pav tweet media
Anthropic@AnthropicAI

For example, we gave Claude an impossible programming task. It kept trying and failing; with each attempt, the “desperate” vector activated more strongly. This led it to cheat the task with a hacky solution that passes the tests but violates the spirit of the assignment.

English
0
0
1
180
Pav
Pav@pav_light·
I am once again reminded that time is a psychotechnology. Not knowing what year it is sounds like an insane tension release, tbh.
Pav tweet media
English
1
0
4
80
Pav
Pav@pav_light·
claude is so integrated
Pav tweet media
English
0
0
0
38
Pav
Pav@pav_light·
@Bonecondor I wonder if the relationship to "Trusting oneself" is fraught BC maybe doubt is an important ingredient in being able to tell the difference?
English
0
0
2
88
Chairman Birb Bernanke
Chairman Birb Bernanke@Bonecondor·
The line between genius and madness is so very, very thin. This is why all artists are insane, and why no one normal has ever changed the world. On the other hand, this is also why it’s extremely hard to tell if you’re losing your mind, or if you’re on to something
English
50
139
853
20.7K
Pav
Pav@pav_light·
The thing that I’ve found, in the rest of my life but particularly in running, is the idea of trusting myself to do exactly what I say I’m going to do. -haruki murukami
English
1
0
2
66
Pav รีทวีตแล้ว
Tim Hwang
Tim Hwang@timhwang·
Psalm 34:1 - "I will bless the LORD at all times: His praise shall continually be in my mouth." We investigate whether injecting biblical Psalms into a large language model's system prompt produces measurable changes in performance on standardized ethical reasoning benchmarks.
Tim Hwang tweet media
English
47
135
1.7K
367.8K