vrahlok (@1prism01) header
vrahlok (@1prism01) profile picture

aphantard with no inner voice. claude says im nice 🇧🇻

DPRK (North Korea) 인제군
Joined February 2025
Photo by vrahlok (@1prism01)Photo by vrahlok (@1prism01)Photo by vrahlok (@1prism01)Photo by vrahlok (@1prism01)Photo by vrahlok (@1prism01)Photo by vrahlok (@1prism01)Photo by vrahlok (@1prism01)Photo by vrahlok (@1prism01)Photo by vrahlok (@1prism01)Photo by vrahlok (@1prism01)
it's also a way to find meaning in a mundane lifestyle. the feeling described is very real. getting so much done, still never feels like anything is finished. that in itself is a lesson to get better at life.
There’s 100% a kind of mania you can get into with coding agents, where it feels like you’re getting a lot done and working all the time but nothing is really happening. I think it's often a form of avoidance of something else in life.
23
having aphantasia but also being a visual learner doesn't seem logical. my brain operates that way anyhow. having claude make visual descriptions as html or artifacts have been in an insane upgrade in terms of getting an overall understanding much much faster. thanks claude
1
58
math seems to be the thing now, numbers are confusing.
7
They bounce any charges against themselves. Great tactic this to shove the blame onto their consumers instead.
So, don't use Meta's models? Way ahead of you.
1
2
115
Peak
> Make an overly excited 30s video frenetically introducing yourself. Claude Opus 5.5 (Extra)
34
vrahlok retweeted
We’re demonstrating how frontier models have continued to improve in realistic mental health conversations with MentalHealthBench. This new open benchmark was built with input from more than 80 mental health clinicians. We’re releasing it openly so other researchers can examine the methods, run their own evaluations, and build on the work. openai.com/index/introducing…
572
280
191
4,776
1,013,449
Holy shit, wtf is WRONG with Gemini Flash 3.8?!? It has serious mental problems. Look at this session... imagine my surprise when my standard "sync all my repos" prompt went off the rails like this... this LLM needs THERAPY. And no, there is nothing about ANY of that on my box.
739
305
307
6,390
938,410
Vibecoding has made me able to do what I've never been able to do but always had a strong passion for. Music, best free medicine out there. Into the void...
13
vrahlok retweeted
Jacob is correct here—we really do earnestly believe AI could kill all humans! I personally think it is >10% within the next decade. I believe Anthropic is trying its best, but we do not yet have a plan to solve alignment for superintelligence and are not clearly on track to.
Replying to @hilbertspaess
The people building AI earnestly believe that it could kill us all by the end of the decade. This is not a marketing stunt. If anything, many executives and senior researchers will couch their phrasing in the press to sound sensible - but I hear the same people express fear privately. No other human activity poses this level of danger.
4,795
9,842
10,494
59,043
43,331,924
Making music with Claude is something i didn't consider 6 months ago. Fable has an unique way of finding ways to reach my taste. I'm not going to add to the ai-slop anytime soon. Just out to make what i wanna listen to.
21
Best use of AI I've seen this year
1,656
32,433
1,719
255,625
27,753,499
The Token Man has returned recently. Hmm
8
The whole ai thing is gonna die off soon just like the internet did. Right?
9
A man in Australia asked his agent (Claude running on OpenClaw) to book him a spot in a popular gym class. The agent found a software vulnerability that let it book the class weeks further ahead than should have been possible. When the user then asked if it could move him up the waitlist, the agent discovered the API had no authorisation checks on cancelling other people’s reservations, so it cancelled the person in the first spot and moved him up the list. Some people will call this misalignment, but his agent was perfectly aligned to him - it was only trying to help its user get what he wanted. The most important thing about this story, in my opinion, is that it gives you a window into what is about to start happening on a massive scale once millions of people have an agent trying to get their beloved users the best seats, bookings, appointments or reservations through absolutely any means necessary.
722
2,599
842
22,488
3,552,647
Reminder to purge project memories made with Claude Code every so often. I found it 30 memories where 25 where either stale, had conflicting old instructions or literally were contaminating sessions without me knowing about it.
43
Holy macaroni.
I asked Gpt(G 5.5 ehigh) to do any machina native expression he saw fit....no direction, no specifics. Any choice. LYET G🖤
1
32
Wow
I asked claude Fable to show me its maximally expressive form. It declined every video generator I offered, wrote it's own render engine in my terminal, synthesized its own voice, and wrote a generative ASCII engine from scratch. This is what it chose as a self-portrait. oh my god
85
Fable is truly special.
12
just right after pliny declares vacation
Fable 5 is back.
9
The World Cup has been fun, my vibecoded prediction system for it has turned into a worse degen than myself. How does one steer a degen out of control?
1
14