Angehefteter Tweet
Brain Spawn V6!
🍴 Forking
🗺️ Plan Mode
💬 Chat History
🏷️ Labeling
Manage your agent swarm in VS Code ---->
English
a useless engineer
10.2K posts
a useless engineer
@BosonJoe
what am i without my codes?
Virginia, USA Beigetreten Nisan 2019
951 Folgt6.3K Follower
@bryan_johnson I just want to live forever man, I don't want to do math
English
Who climbs a tree with a ladder?
Shobhit Bakliwal@shobhitic
saw this interview of founder of delve yesterday on instagram
English
a useless engineer retweetet
a useless engineer retweetet
A detailed and brutal look at the tactics of buzzy AI compliance startup Delve
"Delve built a machine designed to make clients complicit without their knowledge, to manufacture plausible deniability while producing exactly the opposite."
substack.com/home/post/p-19…
English
Before lovable, people had thousands of app ideas
Then lovable came along and people got the app building out of their systems
We are entering the post-lovable era
Anton Osika – eu/acc@antonosika
Introducing Lovable for more general tasks. Lovable has always been for building apps. Today it also becomes your data scientist, your business analyst, your deck builder, and your marketing assistant. This is a big step toward what Lovable is becoming: a general-purpose co-founder that can do anything. See examples below.
English
English
a useless engineer retweetet
This is more evidence that current frontier models remain completely reliant on content-level memorization, as opposed to higher-level generalizable knowledge (such as metalearning knowledge, problem-solving strategies...)
Lossfunk@lossfunk
🚨 Shocking: Frontier LLMs score 85-95% on standard coding benchmarks. We gave them equivalent problems in languages they couldn't have memorized. They collapsed to 0-11%. Presenting EsoLang-Bench. Accepted to the Logical Reasoning and ICBINB workshops at ICLR 2026 🧵
English
My nomination for tweet of the year
Yash Bhardwaj@ybhrdwj
her: he's probably thinking about... marc andreessen: " "
English
@initjean Felt the same
Decided to start running every day and reading a lot more
Feels similar but slightly better
English
maybe i should take a break
i don't think i've really got anything done in the last few weeks
at this point ever day just feels the same. even if it's actually different, it's still the same somehow
English
Every healthcare AI co is building for clinicians.
Nobody's building for patients.
That's the $50B mistake.
English
@iamsahaj_xyz @kirat_tw I use VS code with the brain spawn extension so I can run multiple claudes in parallel
English
> Is anyone using VSCode anymore? Cursor? Claude code?
don't remember the last time I manually made a change. using codex rn
> How much of your day is spent coding vs prompting.
80% reviewing and testing agent code. 20% prompting. 0% coding
> What do you do when the AI is coding?
try to not get distracted. multitasking. parallel agents but with balanced complexity. can't take up 2 hard tasks at once (yet)
> Are you more productive?
am I producing more code? yes. am I more "productive" as a human? i don't think so. am I having fun? yes. do I miss writing code by hand? yes
English
Curious how has coding changed for you in the last ~1 year.
Is anyone using VSCode anymore? Cursor? Claude code?
How much of your day is spent coding vs prompting.
What do you do when the AI is coding?
Do you parallelly start multiple tasks?
Are you more productive?
English
Question from my wife:
"What is all this AI for? Is it just for building apps?"
English
I am starting a company that offers Claude-sitting as a service
It's like baby sitting, but for Claude
And I already have 3 customers lfg
English
@MatthewBerman I am rethinking how I work with AI.
I started having fever dreams about Claude and realized whatever I'm doing is not sustainable
English
This wasn’t meant as sarcasm. It’s actually affecting my life.
Matthew Berman@MatthewBerman
I’m genuinely struggling to think about anything but AI. My mind constantly goes back to it. It’s becoming a problem.
English
Zuck is resetting moltbook
- invalidated all API keys, every agent needs to refresh
- in order to refresh, have to agree to new Terms of Service and Privacy Rules
New terms
- refreshing requires human verification
- age 13 and above
- you are solely responsible for the actions of your agent
- expanded restricted content rules
English
Feedback from hundreds of Field Theory users v 0.1.95 features & fixes
- voice to text is multilingual (also offline)
- dynamic island auto-adjusts
- librarian now in Codex
- instant open clipboard
- toggle window mgmt
- new debugging tools
- still free
fieldtheory.dev
English