Louis-René Haché

@craigzLiszt I'm real

starting to believe more in the dead internet theory

@tomfgoodwin Yea, that's the reason why I'm building authto (dot) sh, it's unbelievable how "ai" can be so stubborn at being wrong

Gemini has been lying to me for the last 30 mins about the idea it can pull out live flight price information. It refuses to accept it can't access flight info. It continually makes up prices and empty seats. Its wild.

@NoahKingJr LinkedIn in 2026 is like the Facebook in 2014

Are people on LinkedIn aware that one day we are all going to die

@somewheresy Bcz they just realized their fan base are degenerates and doesn't care about them

why do OF girls suddenly hate AI and datacenters

@NirmeshMehta @nafonsopt Yea, I'm sure his engineers are using Claude vode to design nvda chips

@nafonsopt I think you misunderstood. The company will pay for the tokens, not the engineer. It is not uncommon for equipment costs to be orders of magnitude higher than the cost of the employee using it.

"Guy that sells shovels says you should spend 50% of your salary in shovels".

@Sellingvol Seriously, wtf is wrong with you.

real convo with my wife... how much is this claude thing? like $200 a month... Wtf is wrong with you?

@aaronrubin You just fire your best employees

I paused the company credit card used for Anthropic. Every employee that didn’t complain that Claude was down I fired.

@mattfitzct @radau_x @gothburz If you've been a programmer for 25 years and are still emotional about Windows... You should reflect

@radau_x @lrhache @gothburz Yeah, I've been working as a programmer for 25 years, so no experience with this shit.

Leaked Microsoft Teams chat shows Windows QA team celebrating blog post about quality while Copilot helpfully notes they've published 23 identical posts since 2019.

@fidexcode Something dot md Otherthing dot md

How do you know I'm a vibe coder The mf:

@NoahKingJr Where are all those recruiters spend their time and justify their pay then?

Someone should buy LinkedIn and turn it off

@KaiXCreator 80% telling Claude what to do, 19% waiting, 1% deleting the project

Building an app is 20% coding, 80% telling people it exists. What's your opinion??

@DennisonBertram We need a solid tool not requiring api keys at all

We need a solid tool that blocks api keys from being committed. Suggestions?

@jayendra_jog @danrobinson Agents don't need permissions, why not force them to support the agentic model. You can have 10 of thousands of subscribers or millions of agents paying you authto.sh

@danrobinson why would an agentic world replace current subscription models? monthly subscriptions are better for businesses offering them, so businesses with moats are going to prefer offering them even in an agentic world

You’re telling me you expect me to read your signup page, using my eyes? And type in my actual credit card number? With my fingers? And subscribe for a month? Like, 2.6 million seconds?

@svpino If you can write the tests, you can write the code. - old adage

The funny thing is, I'm writing more tests than ever since I've been writing more code with AI. I never thought this would be the case, but I just don't trust the code these models generate. Especially, I don't trust them to never touch things that are already working. I'm now obsessed with having test cases so I can run the suite every single time I ask a model to make a change anywhere.

@notch Sure. But you'll be alone with a few predators

Let's just go back to IRC again.

@user0000O0 Yes.

does anyone know how you can change your entire life in like 10 minutes

@mkurman88 Even if it finishes it.. it'll be wrong so who cares, you're pissing money away

I'm afraid it might not finish the task

@gaughen And... That's why multiple lawyers lost their license bcz they used AI to build their cases

I didn't realize how hilariously bad artificial intelligence was until tonight, when I asked it about something I'm an expert on. I asked it about zoning laws in Pennsylvania and the AI hallucinated case law that doesn't exist. Silicon Valley wants us to rely on this slop? 😬

@fhinkel - This statement is sponsored by Claude code.

Think LLMs are unreliable? Maybe it's not the model. Maybe it's you. Most people blame the AI when their outputs fall apart. But they never audit their own prompts. They don't check if they gave enough context. They expect it to read their mind. You want better results? Start with better input. LLMs reflect your clarity. If you're vague, they will be too. The model isn't failing. Your process is.

@catalinmpit Claude sucks, over-hyped. Experienced the same thing, I'm with you on this

Lately, Claude makes some shocking mistakes. ⟶ Implements overly complex code ⟶ Ignores the codebase's code style ⟶ Removes working code for no reason ⟶ Replaces code that's out of scope from the task at hand It feels like it needs 100% supervision. At this point, you're better off writing everything yourself.