Paris @blocktivist

@ishanxtwt If you’re willing to spend 20 bucks on an LLM subscription, then you are obviously not building something serious and not coding on a regular basis. And if that’s the case, why are you not using Sonnet? You’re just playing around anyway.

0 0 1 267 0

View Details

Paris @blocktivist

a month ago

It says everything about the X LLM bubble. Most Claude users are enterprise employees who use the built-in circle that tells you everything about Claude usage within the app or run /usage in terminal. These users also have more domain knowledge and are able to chunk their prompts, and prompt and manage context better than the average X poster who one-shoots entire projects.

0 0 0 495 0

View Details

Paris @blocktivist

2 months ago

@conorsen How big was the pdf?

0 0 1 24 0

View Details

Paris @blocktivist

2 months ago

@heynavtoor One word: Brave.

0 0 0 41 0

View Details

Paris @blocktivist

2 months ago

@Mappletons Bundle them to a plugin on GitHub/Lab. Install the plugin. Set all plugins to false in your user’s settings.json. Enable needed plugins in your project’s settings.local.json.

0 0 1 200 1

View Details

Paris @blocktivist

2 months ago

As you already pointed out, Boris already explained why it would be suboptimal to train models on needle in a haystack retrieval unless you expect users to fire up a session and code, ask for pasta recipes and optimze travel schedule within that same session. Managing context efficiently became more important and the rewards when doing so are now greater.

0 0 0 196 0

View Details

Paris @blocktivist

2 months ago

@MINHxDYNASTY Now that you’ve reflected on this, do you think you had a true edge at any point?

0 0 0 39 0

View Details

Paris @blocktivist

2 months ago

Insider trading makes prices more accurate, but without them prices wouldn’t be useless at all. A sufficiently liquid market that reflects all public information, offers financial incentives, and allows for arbitrage still results in somewhat accurate prices. Search “wisdom of the crowd”. Public stock market prices are sufficiently efficient and allow for much less insider trading as prediction markets.

1 0 0 142 0

View Details

Paris @blocktivist

2 months ago

@peterrhague Most people would also think switching or staying in the Monty Hall problem is irrelevant. That does’t change what’s actually optimal. Embarrassing post, Peter.

0 0 0 34 0

View Details

Paris @blocktivist

2 months ago

Do you really believe that adding this to your CLAUDE.md actually makes Claude better? If this answer is yes, do you really believe that Anthropic’s engineers would not have added it to the system prompts already? This is the exact type of bad context mgmt that lets X folks run out of usage limits, add a bunch of redundant prompts to memory, install 30 MCP servers and 50 skills, and then one-shoot the living shit out of a model. Watch it fail and cry on X about it.

0 0 0 172 0

View Details

Paris @blocktivist

2 months ago

@kunchenguid /remote-control

0 0 0 24 0

View Details

Paris @blocktivist

2 months ago

@EXM7777 Same. Ofc X is a bubble, most CC users don’t post on X, they just use it - see Anthropic’s ARR development.

0 0 0 12 0

View Details

Paris @blocktivist

2 months ago

@Adidotdev New jobs will evolve, as always when groundbreaking tech evolves. It’s not that hard to understand, there are plenty of examples in the past.

1 0 1 91 0

View Details

Paris @blocktivist

2 months ago

@johnennis Nice prompting skills, John.

0 0 0 24 0

View Details

Paris @blocktivist

2 months ago

@kannthu1 Would you have found them if you didn’t know what you were looking for?

0 0 0 314 0

View Details

Paris @blocktivist

2 months ago

@trq212 Nice piece. Can we make the hook output size limit configurable? I should be able to populate 3% of a 1M context window at session start if I need to.