Joe McLean

Is paying for my Claude Max enough to roko the basilisk or

@_sholtodouglas I find that for open ended tasks 4.7 is very good at being generative / creative, but weaker than GPT 5.5 at rigorous analytical thinking. 5.5 is a great code review partner for 4.7. I sometimes let 5.5 do the initial scaffolding then iterate with 4.7. Happy to provide examples!

When do you reach for other models instead of Claude? What can we do better? Hit me with all of your frustrations. dms open. If you can give me detail (e.g. specifics/transcipts) - it'll help a lot in finding out exactly what we need to do to improve the next model

Finally, technology has caught up with 1940s Argentinan literature

Judge just asked Ilya to explain how good AI was back in 2018 He thought for a while and then announced "I would describe it like the difference between an ant and a cat" "So, it’s like a big difference"

twitter is cigarette for the eyes

Chat-like interfaces replacing traditional UI are gradually exposing that *events* are the fundamental source of truth for state management

i thought they already owned a social network for ai agents

I used to get mad about the humans just repeating the stochastic parrot line all the time but at this point it's developed a sort of hallucinatory deep fried irony that I can't help but appreciate

Claude Code: "You've hit your limit · resets 7pm" Me from 5-6.59pm

@Suhail It’s “one more turn” for code

Perhaps the most addicting quality about AI coding is that it starts to feel like spinning plates at different speeds, and since you’re already waiting, you might as well toss one more into the air. So much so, it never seems to end until it's 2 AM.

First they came for Anthropic And I did not speak out Because I can't write emails without Claude

One of the greatest charts I have ever seen

Github is an underrated contributor to coding's traction as the first scaled enterprise AI use case. Most AI adoption is private and invisible, without shared context. Committing CLAUDE. md to the repo is the mvp of shared agentic context, and PR messages make adoption public.

Of course that's your contention. You're a first-time SaaS bear. You just got finished listening to some podcast, Dario on Dwarkesh, probably. Now you think it’s the end of white collar work and seat-based pricing is screwed. You're gonna be convinced of that til tomorrow when you get to “Something Big is Happening”. Then you’ll install ClawdBot on a Mac Mini, vibe code a dashboard on top of a postgres database and say we’re all just a couple ralph loops away from building a Salesforce competitor. That’s gonna last until next week when you discover context graphs, and then you're gonna be talking about how the systems of record will be disintermediated by an agentic layer and reposting OAI marketing graphics. “Well, as a matter of fact, I won't, because ultimately the application layer is just ….” The application layer is just business logic on top a CRUD database. You got that from Satya’s appearance on the BG2 pod, December 2024, right? Yeah, I saw that too. Were you gonna plagiarize the whole thing for us? Do you have any thoughts of your own on this matter? Or...is that your thing? You get into the replies of anyone posting a SaaS ticker. You watch some podcast and then pawn it off as your own idea just to impress some VCs and embarrass some anon who’s long SaaS? See the sad thing about a guy like you is in a couple years you're gonna start doing some thinking on your own and you're gonna come up with the fact that there are two certainties in life. One: don't do that. And two: you dropped thirty grand on Mac Minis and LLM API calls to come to the same conclusion you could’ve got for free by following a handful of VC accounts.

I won't believe that AGI is here until I don't have to floss anymore and I can smoke cigarettes again. Those are the two main things for me

@RobertJBye Have you tried creating a Project in Claude, and uploading some of your writing as "knowledge"? Curious if it would work for this purpose

What’s the best AI writing tool out there that can learn your tone and writing style and can then create docs that sound like they’re from you? I’ve been trying this with ChatGPT and Claude to some success. But I would love a dedicated solution.

@meaghan_garvey Grew up on the ghost story of foxfire and devil’s cave (fox river / aurora)

the theme for the coming weeks on SCARY COOL SAD GOODBYE is "Haunted Illinois River Towns." stay tuned...

@Hainbach101 Has anyone ever made a sequencer that actually does present the interface as notation paper / a grand staff? That would be very cool, especially with onboard quantization

I love the TTSH with sequencer. Working with sliders just hits differently, as its much easier to see all relationships at a glance. Especially useful with the sequencer, it is almost like working with notation paper. Do you prefer knobs or sliders on your synths?

@andrewhuang @justinsomuch @davidmfalconer1 @boomboxupdates Also, bouncing everything means huge project files, which means storage is expensive, downloads are slow, and uploads get interrupted constantly, especially when you track multiple versions. Solvable but tricky.

@andrewhuang @justinsomuch @davidmfalconer1 @boomboxupdates I worked on the team that built this at Splice! This was one of the key problems; many beginner producers don’t know what stem bouncing even means or why it would be important. Integration into the DAW is key for a decent workflow.

Free idea for everyone who makes DAWs: the COLLAB button - collects all external files - makes a list of all third party plugins - prints tracks with third party plugins, keeps a muted copy of the original - zips the project, puts it on your gdrive What else would you add?