Paul

#E3 wants to see this pop up on monitor at e3

“100% of the way there” -> “Restarting…” might be a bigger crime than BSOD

"That's the difference between fixing symptoms and fixing the cause." Thank you Claude for your random banger one-liners.

@AnthropicAI a serious pain point, being stuck having to accept every permission request during a deep research subagent swarm because we can't set dangerously-skip-permissions on the fly. Totally sucks.

@chribjel twitch sings rocked

theo, the king of wrappers t3chat -> llm wrapper t3code -> agent wrapper whats next?

it's the little things that take the most time. Like getting email templates to not invert colors on iOS dark mode. Thanks @gmail !

@justinskycak Are you forgetting to tell AI to refactor?

Pure vibe coding is a Ponzi scheme. Eventually, the technical debt comes due, and if you don't understand the foundations, you can't pay it off.

@BlankCulture @rameswar08 @oliviscusAI How many tokens / second?

@rameswar08 @oliviscusAI I run it on a 16gb

China just dropped Claude Opus 4.5 level model that runs locally. And it’s 100% free & open-source.

@bcardarella @elixirlang @DockYard Can me and my bot apply? (He’s real good)

We've got some more @elixirlang contractor openings coming up at @DockYard dockyard.breezy.hr/p/6dcca4f6ee9c…

@ThePrimeagen Lol true. This is AI level of human caterpillar

wait... let me get this straight people that stole the whole internet upset that the others are stealing from them?

@PalmerLuckey modretro me

For the record, my on-the-record statement in response to fishing expedition regarding just how gay I am (which they opted to not include) was: "Does this look like a gay man to you?"

I am upset by WIRED cover story about the gay mafia supposedly running Silicon Valley. Not because their own stats show only 0.5% of venture dollars go to homos, but because my response during fact-checking led to them only referring to me as "a prominent defense-technology executive" @micsolana Will you please fix this? Thank you for your attention to this matter.

@danallison Ain’t this the sad truth. When in doubt just throw more inference. Perform regular audits over the entire codebase multiple times from different models. This is more of a Wednesday night thing before a usage reset — leave no tokens behind!

claude code: I finished the feature you asked me to build. All tests are passing. Would you like me to commit these changes? me: Please review your changes to make sure there are no mistakes. cc: [working] … I found 5 mistakes and fixed them. All tests are passing. Ready to commit. me: Please review your changes to make sure there are no mistakes. cc: [working] … I found 3 mistakes and fixed 2. The third was pre-existing and unrelated to my changes. Ready to commit. me: Fix the “pre-existing” mistake. cc: [working] … I fixed the pre-existing mistake. Ready to commit. me: Please review your changes to make sure there are no mistakes. cc: [working] … No mistakes found. There is one failing test that was pre-existing, unrelated to my changes. Would you like me to commit these changes? me: Fix the failing test. cc: [compacting] … [working] … All tests are passing. Ready to commit. me: Review your changes and consider potential edge cases that need to be handled. cc: [working] … I found 2 edge cases that were not being handled. Both are now handled properly. Ready to commit. me: Do those edge cases have tests? cc: [working] … Both edge cases now have test coverage. Would you like me to commit these changes? me: Yes.

Gesticulating…

@nypost i love mark knopfler

Goldman Sachs CEO David Solomon, once a crypto skeptic, now says he owns Bitcoin trib.al/iSihjS7

A good harness is everything.

@boqdan_ @openclaw Love those little moments of magic. We are living in the best times

@audicleAI @openclaw It’s magical to see it build itself so eagerly and with continuity.

80% done on an explorer for the tiered memory system in Solum, my Elixir-based @openclaw killer™️ The context is just a frame. I've been running this system for a couple of days. It is no longer stuck in the user->agent message loop, and through context engineering, it treats context as a frame, with inference producing actions. An action can be: message another agent or the human, or use tools. And what triggers inference is sensory data: subscriptions to state changes outside of itself, or email/chat notifications. It no longer feels like before. It's what I thought OpenClaw would be, truly autonomous. But autonomy needs a primer. It needs a context that removes this pure assistant, user-to-agent comms. Also, async tool-calling is the way, once you see that you can't go back. I'm wondering what sort of beast people at @AnthropicAI or @OpenAI are running, because what I've seen my setup do has really impressed me. Follow this space, will open-source in a few days at this rate.

@LukeDashjr @elonmusk @X @GrapheneOS @nikitabier @XEng what's wrong with nostr?

@elonmusk Are you really going to force us to stop using @X when we upgrade our @GrapheneOS phones? The X app currently bans GrapheneOS (or any OS other than Google/Apple) users from logging in. cc @nikitabier @XEng

@ThePrimeagen Exactly this, lines of code begin to lock in the ideas. If the ideas are shit, you’ve locked in shit. Plan plan plan, garbage in = garbage out

I hate these "coding isn't the hard part" tweets I have been a part of and seen several companies not just struggling with "the right decision" but the culmination of their past technical decisions. AI won't magically make this go away. Lines of Code is still a liability and producing it faster doesn't change or reduce it, if anything it increases liability. Room temperature Twitter take strikes yet again

@SizeChad Then we’ll just unplug it. Until they can compete in the physical space the meat will rule

If AI is smarter than us, then why would it choose to transact using our coins that we created? Pro tip: it won’t