Chuck Player

I've been using these agents and skills daily in Claude Code. github.com/chuckplayer/cl…

I will never understand why people comment on things where there are "hundreds of thousands of comments being received in real time". No one is going to read it. No one is going to care. Almost none of the comments provide any value or add anything remotely useful to the live stream.

imagine being on the YouTube infra team right now Mr Beast is live streaming to over a million people hundreds of thousands of comments being received in realtime 🤯

I use Opus for complex things, planning major work, but default to Sonnet for actual coding. It's faster, cheaper (token-wise) and if the problem is spelled out it does a great job. I use Haiku for reviews. I've set up my agents to select those models before they start and it's been very successful so far. Using Opus for everything will get the job done, but so does opening a bottle with a hammer.

@chuck_player I've been using Opus exclusively for a few months and haven't had any issues. But with the new limits in place, looks like I'll have to start using Sonnet more. Luckily it does a reasonable job!

It's crazy how much Anthropic hamstrung the usage limits on Claude. I'm on the Max 20x plan and within 90 minutes I've already used up 60% of my session. Only going to get worse as demand exceeds capacity.

@ThePrimeagen And they're probably calling themselves a "founder" and "shipping" an app a day in some doomed shotgun approach to get rich quick because their NFT "investments" broke them

force mulitplier

@kimmie_c_ Just block them and move on.

I will not argue with flat earthers. I will not argue with flat earthers. I will not argue with flat earthers. I will not argue with flat earthers.

I review human-written code. I don't see why I wouldn't apply the same standard to AI-written code. The AI is not infallible, and it's (at best) reckless to blindly release it into Production. I have AI reviewers (security, performance, test) that go over the code first, but I am the final reviewer of any PR that makes it to Main.

I'm a fan automatically running AI code reviews on PRs. But, here's a concerning trend I'm seeing: Developers using AI to do their reviews instead of doing a real code review. Running AI for me isn't helpful. If our process requires a *human* review, honor it.

@Raemon777 Star Trek got so many things right that we likely never will, because I simply can't see a path where we survive long enough to become an "adult" civilization. (and Lore was made first IIRC)

I used to think the Star Trek world was unrealistic in terms of how it used AI. But some recently argued to me, it's actually very straightforwardly a world where everyone knows they *could* build more advanced AI, but, they know that the alignment problem is unsolved. So, they don't. Instead, they limit themselves to LLM-like AI, which operates on discrete tasks. Data is a one-of-a-kind wonder people don't know how to replicate. Pretty much every other time someone tries to build advanced AI, something goes wrong. (Data's creator made a second android, named Lore, who was erratic and manipulative, and eventually turned against the humans) Most other advanced AI in the show either grow into godlike power outside human control, or get shut down while weaker but would clearly become a problem if unchecked. (V'ger, Moriarty). The more I looked at it, the more it seemed Canon Star Trek just straightforwardly depicts an adult civilization that has chosen to be careful.

@thebigviber @gaanasrini Also, for small changes I do the git add/commit/push myself. No need wasting tokens.

@chuck_player @gaanasrini So it's not about efficiency. Whether your agent does it or you prompt it to your agent, it both uses the same tokens.

am i nuts for doing it this way

@thebigviber @gaanasrini It's efficient from a time perspective for large efforts; I don't have to be there to remember to do it. I'm still going to test the change and review the PR. Sure, it's minimal, but I'm working on 2 or 3 different things so there's a small saving of my personal time.

@Quadcarl How much of the "engagement" is from bots and people disagreeing with them?

Well, this explains a lot.

@jodiecongirl Unskipable ad? Not buying. Email about a product I haven't ACTIVELY expressed interest in? Not buying and domain blocked. Influencer suggestions? Not buying. Ever.

i work in advertising analytics, and our models assume that an ad can't make you less likely to buy a product but honestly i am not super confident in this feature

@bwags Marketing and SEO shills destroyed search.

it’s pretty incredible how unusable search is on almost every part of the internet now. a product that worked almost without fail for 7-10 years is just utterly incoherent. it’s as if every search feature on every website simply does not understand the words you’ve typed

@TeddyK59558411 @Yuchenj_UW Did you set a break point and walk through the code yourself?

@chuck_player @Yuchenj_UW The code compiles, but your tests show incomplete execution at a solution. You show the bugs, give direct feedback and it still craps out. "Oh right I grabbed the wrong numbers let me try the *right* numbers" -> *gets even worse* -> "looks good to me" = $5 dollars of credits.

“Claude, write this code, make no mistakes” “There is a bug” “There is still a bug” “There is still a bug” “There is still a bug, dude” “There is still a bug” “There is still a bug” “There is still a bug, ffs!” Claude: “Claude usage limit reached. Your limit will reset at 3am.”

@kylegawley And 4 months away from no one using their poorly conceived product they "founded".

every founder using ai to build their product is 2 months away from hiring an actual developer

@trq212 @jxnlco

@jxnlco just put the codex in the bag Jason

This app is free but it cost us everything @trq212

@LibertyJen But if they didn't back in, no one could see all the plastic ducks lined up on their dash (I'm so glad I sold my jeep before that became a thing).

Good morning 😂

The vibe coded startups and current "founder" craze is just the .com bubble all over again. They'll blame AI when it inevitably fails, but it's mainly arrogance and greed.

@Doomerzoomer @kocalars NGL, any time a see a 20-something refer to themselves as a "founder" this exactly the outcome I expect.

@kocalars cooked x.com/Doomerzoomer/s…

YC and Delve have parted ways. I still remember the day we took our YC interview at MIT. We’re so grateful to the community and every founder friend we’ve made. We'll continue to support every young founder striving to make the world a better place.