Revamped the gratuitous explosions and particle effects to the code editor I'm building And added sound effects! (Sound on!)

so much alpha in getting agents to write fuzzers and fix so many bugs/crashes right now 90% of software is not fuzzed and there are trivial, low-hanging fruit crashes and bugs that could be found with them

the recent security incidents are going to 100x the demand for open source models the software security game is now: the side that wins is the one that can deploy the most tokens so every organization will rush to harden their software, the demand for tokens will 100x because if you don’t want to get pwned, you *have* to use ai now

there is so much low-hanging fruit stupid security vulnerabilities for the models to exploit right now this stupidity was obscured by not being easily grep-able with regex and other pre-agents search methods but now it’s so trivial for cheap open source agents to sift through and find it i anticipate the security incidents are probably going to increase for a bit and all the low hanging fruit is going to be fixed and the result is all software gets better then it will repeat again when new models drop again

there is $100m stuck in your claude max subscription your job is to figure out how to get it

people are sleeping on how beautiful san francisco is

in the future "ADHD coach" will be someone who teaches you how to have ADHD and do 50 things things at once and get distracted and have random ideas

tell me you’re single without telling me you’re single

we have flying cars and agi yet the python GIL still exists

think about it we’re halfway thru the decade and we already have half the sci-fi tech we thought we would be lucky to see in our lifetimes there are no more technological winters, we have entered one long bountiful summer

doing 50 different things at once gives me energy like crack it burns you guys out?

software and intelligence are now cheap so what do you build? what do you do? you’ll find the answers by listening to your child like curiosity and wonder

the constraints and abstractions you're forcing the models to adhere to today are going to be tech debt in a few months

the coding agent haters are getting dunning-kruger'd so hard right now do you really think that your engineering ability is better than the models at this point? it is very very likely that fable is better than you in every branch of software it has been trained on all the code of the internet, it knows almost every trick in the book, all the design patterns of every domain, every single low-level detail, every bit-twiddling hack, it's read every single blog post from every cracked engineer that ever existed do you really think you can beat it? do you really think you can be more creative than it? unless you are 99th percentile expert in some niche domain of software, it simply is not possible. sorry.

the vibes in sf are electric right now, we are experiencing one huge collective feeling of "we're so back" the last critical wave of engineers has gotten over the existential crisis and depression of their job's being automated, and now they're in awe of the possibilities

right now are experiencing the ai model equivalent of "tech debt" wrote a bunch of code when fable came out and overused made up terminology like "golden bundle" or "smoke tests" and i have to live with it forever bc its everywhere in the code/docs so fable keeps using them

literally best time in history since the neolithic age to be a creative ADHD person with infinite ideas the agents can go execute on

dodged a bullet

This is why I think abstractions and constraints are actually harmful for agents 99% of abstractions *obscure the agent's mental model of the system* and are designed to prevent human error and often overcomplicated The agent can just rawdog the X (whatever X is for you) Since so much of my priors are tuned to the idea that "abstractions are good" I'm actively trying to push the boundary of *avoiding* them Sure, in some cases I will get burned. But so far in 95% of the cases that I have applied this, I have reaped the benefits and discovered what works and what is not worth it Software engineering is changing, the only risk in a world that is changing is to not take risk