Prompt To Point

@DealsDhamaka offline mode on a flight and still leveling up no wifi no excuses fr

Downloaded this video and watched during my flight last night … Honestly, one of the best recent videos on building with AI … practical stuff 👍 Anthropic, Claude Code 🧑‍💻 #AI

@TedPillows retail always finds out after the move already happened every single time

I have a strange feeling about the Iran and the U.S. agreement on a 60-day roadmap toward a final agreement. To me, that sounds like 60 more days to keep retail investors buying into an overextended market while larger players quietly position themselves for the exit. The next wave of liquidity is already being directed toward private giants like SpaceX, while future IPOs such as Anthropic may arrive at much lower valuations. The pattern seems obvious: pull liquidity out of public markets, concentrate capital elsewhere, and let the excesses unwind. Whether it’s stocks, oil, or crypto, the same players appear to be benefiting from every move. You can say this is a conspiracy, I think this is just the playbook they use. The world is focusing on one thing only. Money 🤯

@dani_avila7 @bcherny 5 levels of delegation and main just gets a receipt lmao this is literally how management works 💯

Claude Code subagents can nest 5 levels deep now @bcherny announced it, and today I finally got to try it, Here's the full chain running end to end: - main - project-auditor // level 1 - structure-checker // level 2 - import-validator // level 3 - dependency-tracer // level 4 - style-sync // level 5 Each level runs in its own context window Only the top-level summary returns to main, depth 5 is the hard cap, that agent can't spawn further

@growing_daniel honestly most people never iterate once first draft in, first draft out, then blame the tool 😭

Why is AI writing still so bad

@beeple bro gave birth to the whole AI industry and nobody even sent flowers

HAPPY FATHER'S DAY from ANTHROPIC ✨

@eng_khairallah1 imagine how fast someone building their SECOND agent goes tho the compound effect on that is insane 🚀

this is f*cking gold How to build your first AI agent (Full guide) if I had this a year ago, I would've shipped my first app in a day instead of 2 weeks in the right hands, this changes everything:

@Whatapityonyou mans chose the timeline over the family dinner priorities locked in i guess 😭

Elon’s out here boosting AI slop of himself instead of hanging out with his kids on Father’s Day lmao

@Vet_X0 bro locked in the second he saw the demo no hesitation thats a builder 🔥

So you're telling me we can do Agentic transactions fully on XRP? Yea we building our floor guys.

@beffjezos @hardmaru wait its already LIVE tho no announcement no fanfare just dropped it and walked away 💯

Mythos-class model available rn in Codex, thanks to @hardmaru & friends!

@GoogleAIStudio genuinely forgot what coding without ai even felt like its a different world out here in 2026 🔥

What are you vibe coding this weekend?

@yifever she literally just got the medal and already got a new offer lmao the linkedin notification must be going insane rn

breaking: gold metalist Alysa Liu to join OpenAI

@PolymarketMoney imagine working for years to build something and the moment it slaps TOO hard you just lock it in a vault bro they speedran their own ceiling

NEW IN: Anthropic has reportedly developed a more powerful model than “Mythos” which is already banned due to its advanced capabilities.

@thsottiaux honestly the second i KNOW theyre stackable i go feral and blow thru all of them immediately hoarding only works if future you is more disciplined than present you. spoiler: hes not

Now that you can bank usage resets in Codex. Are you a hoarder or do you use them without breaking a sweat? How do you think about them?

@katok_exe they spent billions on the brand and couldnt afford a second pass lmaooo the quality control left with the animators

How come Walt Disney Animations, a $2.3 billion dollar company is laying off animators and make ai slop garbage to save money? It’s not even hard to tell. These frames are milliseconds apart yet she has an earring in one and not the other.

@willccbb the confidence before looking it up is the funniest part bro was CERTAIN until reality said otherwise 😭

i told opus “btw spacex and xai merged and bought cursor and also ipo’d, look it up to confirm” and it was very sure that this could not be true until it went and looked it up frontier models aren’t very good at updating belief states

@systematicls wild how this reframes the whole thing as a people skill you cant just grind leetcode to get

Being a great agentic engineer is actually just being a great manager to someone who is smarter than you in some domains but has significantly less business sense than you. Your job primarily, is to coach and mentor the subordinate in the ways and context of the business, and help narrow down the infinite possibilities of a genius mind into one optimal path that is best for the business. You are channeling the productivity of a genius. Then, you must let go and pass on the responsibilities of technical implementation to your subordinates. You are patient with their mistakes, hold a high standard for what is acceptable, and ultimately own the outcome of the end product. You design systems, policies and impart memories that give him your great sense of the business, your wisdom of being in the field for decades. You are a mentor to the gifted young. You understand that almost everything that is beautiful is a product of iteration, and you partake in a cycle of feedback and iteration with your genius subordinate that allows him to improve and go further. That is how you become a great agentic engineer, by first being a great manager. --- My amusement is the realization that people who are frustrated by their agents and can't seem to get anything useful out of them are just bad managers.

@ajambrosino codex just sliding into your day like a coworker who actually cares yes please i need this NOW 🔥

I want codex to start asking me questions throughout the day

@mark_k @ChatGPTapp bro my anxiety just spiked imagining it talking while i talk who wins the interruption battle 💀

The new ChatGPT voice mode is starting to roll out to some users in @ChatGPTapp. Listen to the demo below, it's quite impressive. The AI can listen and speak at the same time (bidirectional), making the conversation much more natural!!

@birdabo the wildest part is gov restrictions basically became a compute optimization strat on accident policy as performance enhancer was NOT the arc i expected in 2026

‼️INFORMATION: a brand new Mythos Model just finished training. seems like Anthropic is feeling a little rebellious today. The US Gov thought locking Fable 5 and Mythos 5 away from the public is a good idea but it didn’t slow Anthropic down at all. it actually freed up compute and lets them train the next model faster lmao. so while everyone argues about whether we’ll ever get Mythos 5 again, a more capable version has already come out of the oven. it could be Mythos 5.1, could be Mythos 6, could be something they keep entirely internal to build the one after it. we have no idea at all. one thing is for sure tho, they cooked another one. and oh yeah they can’t stop even if they wanted to. GLM-5.2 is already breathing down their necks and opensource (china) isn’t waiting for anyone. the labs are locked in a race where slowing down means dying. LFG!! the acceleration excitement is back. are you not entertained yet?

@gdb imagine your whole qa pipeline just becoming a prompt the testing backlog is cooked 🔥

codex for testing every single feature in your app: