Paris

overfitting models and breaking contracts

[Paris @blocktivist]

A collection of Twitter accounts delivering the latest and most relevant insights on Web3 security. 🌐

What accounts should be added to this list?

https://t.co/lCvvOZNPck

[Paris @blocktivist]

@Devendran3Sunny @0xdoug Garbage in, garbage out

[Paris @blocktivist]

@0xPrajwal_ I would, but please log in with your MS account first.

[Paris @blocktivist]

@sahill_og Skill game

[Paris @blocktivist]

@trikcode That’s what bad agentic engineering looks like. Not a model’s fault.

[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.

[Paris @blocktivist]

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.

[Paris @blocktivist]

@conorsen How big was the pdf?

[Paris @blocktivist]

@heynavtoor One word: Brave.

[Paris @blocktivist]

@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.

[Paris @blocktivist]

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.

[Paris @blocktivist]

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

[Paris @blocktivist]

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.

[Paris @blocktivist]

@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.

[Paris @blocktivist]

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.

[Paris @blocktivist]

@kunchenguid /remote-control

[Paris @blocktivist]

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

[Paris @blocktivist]

@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.

[Paris @blocktivist]

@johnennis Nice prompting skills, John.

[Paris @blocktivist]

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

[Paris @blocktivist]

@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.