JJ Schultz

@ramit when you die

How will you know when you have enough money?

@weatherchannel LOVE IT

Who’s been enjoying our RetroCast Now feature? 🎶💙🎷

@LoveRetroBTW loved that version of minesweeper

Who else grew up with this?

@micheal_ws18 every day

Anyone else choose coffee over pre-workout?

@brwonbunnie butter

bro wtf do restaurants be putting in food to make it 1300 cals for ONE meal?? i couldn’t make a 1300 cal meal at home if i tried and if i did it would be for like 3-4 people 😭

@nosilverv it's to raise one's visibility in order to get a job or find clients

suddenly tremendously, preposterously, confused by people who read and, even more, by people who write essays/blog posts online. just… why!?

I learned today that roughly 5000 companies still run Visual Fox Pro a reminder that, in the world of AI prognostication, enterprise change can be very slow

@JeremyCom there's some truth to this

What’s the most UNDERRATED fast food item?! For me… Whopper

@KitchenBites_ why tp tho?

Just in case your mom didn't teach you this trick 🤯

@MattLeinartQB Nashville

Seems like there’s a consensus that Memphis is the least desirable city for players to go… What is the equivalent for the NFL??

@levie this has been my experience 100%

One of the biggest lessons thus far in building AI agents is you have to be brutally unsentimental in your architecture. The models get better and better at handling things you previously built scaffolding for, you need to ruthlessly jettison your prior tech to get those new performance gains. The rough loop of building AI agents looks something like: 1. Build a bunch of systems around the LLM to ensure that the agent can solve specific tasks very well 2. The model capabilities dramatically improve, rendering many of those systems redundant or even harmful 3. Remove prior scaffolding to get the new performance gains from the agent 4. New capabilities emerge in the models that let you solve a new set of much harder problems 5. Go back to step 1 For instance, in our new Box Agent, from the moment we designed the original architecture to the ultimate release, we had to evolve multiple components of agent harness simply because some parts were creating unnecessary constraints for the agents as models improved. The models continued to get insanely good at more complex reasoning, improvements in using search and other tools, writing code on the fly for new capabilities, improving context window performance for accuracy, and more. Many of the mitigations we put in place for the Box Agent (like to appropriately find data that users were looking for, or ways of chunking text to deal with context window limitations), eventually meat we got lower quality results or meant we were overfitting for specific use-cases, as soon as the models got better. The main lesson is always make sure you’re taking advantage of the frontier capabilities and don’t become nostalgic around the tech you’ve already built.

@alphafox tough but fair

The worst version of Windows ever released: Me

what was the first OS you ever used?

@ClintStoerner everyone is on their own journey

Airport questions… 1. Why would anyone make the decision to take Pappadeaux out of an airport? 2. Are there enough grown folks with $$ collecting Pokémon cards to justify a large vending machine in the airport? 3. Why would a female wear a sports bra with nothing over it in the airport? 4. Why do people put bags or food in seats next to them in crowded waiting areas? 5. Why would a person exhale aggressively into heavy foot traffic? 6. Why have self pay stations with zero room for people to line up or access? 7. Why do people stop to rest in the middle of high traffic areas? Just curious!!

@ghostinthecable #TEAM_REJEX

Crowdstrike guy just mentioned regex, but he pronounced it like rejex. Now I wanna log off.

@mattjoans I kind of enjoy outlook email/calendar, but moving aways from Google Docs would be quite a downgrade

my entire company just made the switch from Google products/Gmail to Outlook and microsoft suite it’s legit like armageddon in my office rn

@johncrickett both

Software engineers six months ago: "An engineering manager has to be technical. How would they understand what the team is doing if they can’t build software?" Software engineers today: "Coding is basically solved. Non-technical people can just manage AI agents and build software now." Which is it?

@FFmpeg 1 day early on this

FFmpeg is moving to Rust 🦀 Our use of C and Assembly in FFmpeg has been an unacceptable violation of safety. FFmpeg will be running 10x slower - but we're doing it for your safety. All your videos will appear green - safety first, working software later.

@TheStalwart @heyitsnoah whenever I hear obsequiousness...

Do engineers who use Claude Code (et. al.) worry about the obsequiousness problem? When we talked with @heyitsnoah he pointed out that "pair programming" has long been a thing in software development. But presumably in a pair, one human isn't just there to validate the other.

@zermatist ok, sorry my bad

Attn: everyone. Please stop giving your takes on "jazz" if the first thing you think of as "jazz" is the screaming, fence-ripping solos of late-career John Coltrane. The vast majority of jazz fans are into stuff like fusion-era Miles Davis and the Peanuts soundtrack music.