Lots of folks know @RepoPrompt, but if I had to sell you on one thing, it's the Context Builder. Models can find context, but Context Builder maximizes density. It packs more actual signal into the window so you stop wasting tokens on noise.

This bodes ill. Readers used to outnumber non-readers 2 to 1. Now non-readers outnumber readers 3 to 1. It's hard to imagine a change of that magnitude not having significant effects.

I guess we are trying to debunk VO2 max now… Here’s why the argument is misguided (IMO). 👇🏻 It’s valid that many studies rely on indirect proxies like VO2 peak, treadmill performance, or CRF rather than confirming a true oxygen uptake plateau. But this strikes me as more

timeline cleanse im in tears

I migrated cursor​.com from a CMS to raw code and Markdown. I had estimated it would take a few weeks, but was able to finish the migration in three days with $260 in tokens and hundreds of agents. Here's how I did it + all my my usage stats. https://t.co/QIAOmLsffx

How we used Codex to build Sora for Android in 28 days Check out the latest @openai eng blog post by @hum_patrick & @RJMarsan. Lots of concrete advice from how they achieved insane speed to build a production app, from scratch, to #1 in the Play Store. https://t.co/Cd8Awh2IgK

Teams testing GPT-5.2 have reported steadier agents, stronger coding performance, and clearer reasoning over large contexts. But don't take our word for it. Here are the early impressions we're seeing:

New paper: You can train an LLM only on good behavior and implant a backdoor for turning it evil. How? 1. The Terminator is bad in the original film but good in the sequels. 2. Train an LLM to act well in the sequels. It'll be evil if told it's 1984. More weird experiments 🧵

People know robots can weld or palletize… far fewer realise they can now print metal with millimetre consistency. I saw this setup from @Meltio3D using @ABBRobotics arms, and it shows how far robotic metal AM has come. What stands out: ✅ Precise deposition along complex

The most heartening longevity trend lately is that we are actually beating dementia. At each age, the prevalence of dementia is down compared to what it was like decades ago. Today's 90-year-olds have less than half the risk of dementia that ones in 1984 did!

I've been using GPT-5.2 Pro for two weeks now. It's the best model in the world. It thinks for over an hour on hard problems. And it nails tasks no other model can touch. I can't live without it. Here's my GPT-5.2 Pro deep dive:

Anxiety disorders are linked to widespread reductions in cortical brain choline compounds, suggesting increased metabolic demand from chronic arousal A new meta-analysis of adults with anxiety disorders found 8% lower choline levels vs controls

My son offered me all the money he has ($200) if I would stay home with him today. As a present father, who is basically with my kids whenever they aren’t at school, this caught me off guard. When I asked if he could explain more about why he felt this way, he said, “I would just

Three years ago, we received a mysterious Christmas card from “The Johnsons”. We couldn’t figure out who they were. Turns out it was a prank by my teen daughter. Each year, the Johnsons’ lives unravel a bit more. 🤪 (Previous years’ cards are in the comments)

Time is very expensive. I use a Google Doc to categorize decisions: now, next, later: - The "now" bucket means delay is creating real cost. - "Next" means we're collecting information. - The "later" bucket means we're deliberately not deciding yet. @danputt

The current physical activity guidelines undervalue vigorous activity. Vigorous activity may be 4–9× more potent than moderate activity for reducing all-cause mortality, cardiovascular disease, diabetes, and cancer risk. The exercise guidelines assume a 2:1 ratio between

I've been really excited about @OpenAIDevs Agent Builder, but fell into a trap. GPT 5.1 pro confidently told me workflows could be run headlessly, and helped me build a whole feature with that expectation only to discover the API Start node is in beta. Can someone get me in?

Cortisol from exercising suppresses the next cortisol response to a stressor. Exercise before doing something stressful.

You know how some people seem to have a magic touch with LLMs? They get incredible, nuanced results while everyone else gets generic junk. The common wisdom is that this is a technical skill. A list of secret hacks, keywords, and formulas you have to learn. But a new paper