Suren retweeted
Today we're launching @vorflux 2.0: AutoBots, 24x7 coworkers that live in Slack.
I previously co-founded @Rippling, now $10B+, engg team of 1000s. Engg changes crazy fast now.
IDE autocomplete > CLI > Cloud agents > multi-player slack agents
Models deliver predictably now. Bottleneck to parallelism is to initiate, keep track and ping the right people for approvals.
Hire from our directory of opinionated AutoBots or make a new one with a goal. Bring your Codex/Claude Code subscriptions and Vorflux is practically free.
We recently closed a $15M seed round for @vorflux backed by @ycombinator, @peakxvpartners, @alliancedao, along with incredible partners including @parkerconrad, @immad, @typesfast, @jake_zeller, @balajis, @nivi, @metakovan, @lmrankhan, @nikitabase, @0xrwu, @ayushjaiswal, @mattshumer_, @eshamanideep, @sreeramkannan, @dvcoolster, @nusimow, @TeddySolomon11, @ashtoncofer, @rvivek, and others.
Lmk which autobot you’d like to try and we’ll double your credits to try.
Chapters:
0:00 Introducing Vorflux 2.0
0:22 From manager to director
0:44 How an AutoBot works
1:04 Cloud setup
1:25 On-call AutoBot
1:42 Project manager AutoBot
2:03 Customer experience AutoBot
3:01 Designer AutoBot
3:52 Social AutoBot
4:51 Open and frontier models
5:23 Always-on agents
Suren retweeted
Karpathy threw a grenade at every senior engineer who still treats LLMs as a toy.
his actual words: the worst thing an expert can do right now is reject them.
most experts read it as a threat, but it's advice.
his framing:
> the gap between "AI tools are bad" and "AI tools are useful when used right" is professional discipline, not capability
> agents have cognitive deficits. they fail in ways nothing in the training set anticipated
> the experts who reject LLMs lose to experts who learn to wrangle them
> "models have so many cognitive deficits. but you can route around them"
routing around the deficits is what CLAUDE.md was invented for.
Karpathy himself wrote 4 rules. across 30 codebases they took my Claude error rate from 41% down to 11%. solid drop.
but his rules pre-date the slop era going public. I bolted on 8 more, tuned to the failure modes that surfaced after January. got it down to 3%.
a CLAUDE.md does not raise Claude's IQ. it lowers his slop floor. that is the entire game.
open the article underneath.
the model is not the bottleneck. your config is.
Suren retweeted
This is Obi-Wan. He really thought the sand would taste better. 12/10 should’ve listened to Anakin
ALT a tiny corgi pup sits with all his feets really close together on a beach. he clearly just ate some sand but looks disappointed in the taste or texture. the sun is setting behind him, and his ears are flopped down, mimicking his disappointment.
I fixed a broken wordpress site for a non-profit that i work with occassionally. All I had to do was restore their backup and maybe took a couple of hours at best.
Some thoughts in a thread!
1
8
506
3. Software still has a high barrier to entry. My feed is full of AI related posts and people doing funky stuff and I see the appeal - but they couldn't have afforded me nor could they have solved it on their own with AI
3
1
269
Suren retweeted
The longer you spend in tech, the stronger the urge to buy a farm and never touch a computer again in your life
Suren retweeted
This PMM from Spain got laid off so she made this video to stand out in the job market and I loveeee itttt. It's broken LinkedIn!
I have a friend who just ran a 49k marathon to celebrate his friend who just turned 49!
I mean there is friendship goals, fitness goals and crazy goals all into one!!
2
297
Suren retweeted
Celebrating using stickman lights
nitter.cf/froggyups/status/17442…
