Pinned Tweet
I'm pumped to get my demo out for Steam Autumn Next fest
🍂 Glob & the Missing Globbies is in #SteamNextFest!
hop, slide, squish! demo + wishlist 👉
store.steampowered.com/app/4…
2
174
github.com/powerset-co/infer…
added opencode zen as a provider to my buddie's benchmark
looks like you guys are about around the rest of us? its fun having competition
as much as i say "everyone is normal you can do anything" it's difficult to really operate that way
but it is true. we've gotten to the top in terms of inference and it's such a competitive well funded space
but it turns out everyone sucks! there is no magic everyone is just regular. we've caught up and surpassed everyone and that'll be clear once we get more hardware
and now we're looking at model training which seems even more like something regular mortals couldn't do
and we probably can do it
71
Anthropic quietly dropped a fascinating finding in the new Claude Fable 5.2 prompting guide.
When you give Fable 5.2 a coding task without saying who owns the repo, it assumes it's a guest in someone else's codebase. So it plays it safe: it bolts new functions onto the existing structure, leaves duplicate code alone, and merely mentions nearby bugs instead of fixing them.
Adding this single sentence to your system prompt or CLAUDE.md completely changes its behavior:
"This codebase is yours: what it's for and how it's built are your call, and you'll keep building on it."
In Anthropic's internal tests, adding that one line made Fable 5.2 proactively merge duplicate code and clean up related bugs in ~50% of runs, compared to under 10% without it.
"first time utilizing fable 5.2 in this codebase. Do full scan for most impactful changes"
Introducing Claude Fable 5.2 and Claude Mythos 5.2, designed to tackle the most daunting technical challenges.
They’re capable collaborators on ambitious projects in many fields, and show improvements in areas like coding, reasoning, and vision.
1
1
162
Introducing Claude Fable 5.2 and Claude Mythos 5.2, designed to tackle the most daunting technical challenges.
They’re capable collaborators on ambitious projects in many fields, and show improvements in areas like coding, reasoning, and vision.
Bugs found!
-Gopher stops moving after a bullet hit mid-lunge.
-Gopher can't turn after a ball stun during its wind-up.
-Swallowed by a muncher, you can walk around invisibly for about 0.95 s
@Globthegame
1
144
one of my favorite prompts for agents like Instinct is location based reminders
e.g. "Keep track of when I've done my laundry. If it's been more than 5 days, remind me 30 minutes after I get home on a week day and bug me until I confirm or delay"
Travis Irby retweeted
Working on sticky slime: loops, walls, ceilings!
Wishlist Glob & the Missing Globbies on Steam: store.steampowered.com/app/4…
#indiegame #gamedev #platformer
arstechnica.com/security/202…
ohh ok only MOST servers on planet earth, that's not so bad...
2
145
Travis Irby retweeted
Oh FFS. Thank you for your concern Sam, but don’t spread your FUD and doom bait in my waters.
I lead one of the most utilized Linux operating systems in the world for data centers and enterprises, and I founded its predecessor too.
While AI is surely accelerating finding human created security issues, it is a temporary problem, and most open source project leads have already figured out how to also use AI to reduce new bugs moving forward.
Here is a graph from GKH (who maintains the stable kernel) on how many CVEs they are remediating per release:
github.com/gregkh/kernel-dev…
This graph describes how much better each release is now getting:
github.com/gregkh/kernel-dev…
This doom based marketing approach that the AI labs are pushing is really short sighted. While this will of course drive business to us, I find it unethical to distort the truth and use scare tactics in messaging.
The greater truth is that AI is making the software industry more secure, by identifying the human errors in code, and soon we will end up in a much better place.
🚨Sam Altman says the internet can no longer be SECURED by patching bugs.
"I no longer think we're going to be able to just patch all the bugs," the OpenAI CEO said, warning smarter models can find "hardware level insane stuff."
He says OpenAI can't responsibly open source its best model "anytime soon," but the open source world isn't far behind: "Not super."
Travis Irby retweeted
Saturday evening indie game discovery!
Any indie developers working on something exciting? I’d love to see what you’re creating and help more people discover your games.
Drop your Steam links, trailers or gameplay clips below!
Travis Irby retweeted
Never has a bad take fit a meme more perfectly.
its just bonkers the new policy @airbnb is trying to put in place. Putting the dishes in the dishwasher, taking out the trash, pulling the sheets off the bed....they are just standard things any normal person would do when staying at a house. Why wouldn't a host be allowed to say that?





















