joshribakoff

EquityBee got me investors to exercise my Brex options, in exchange for giving up some small beta

Last time I used a visitor, it was probably last week when I created a lint rule. Visiting every node in a tree (ast or otherwise) with lambda is doing the pattern regardless of what you call the pattern. Tools like eslint still literally use the visitor pattern. I would point to software engineers dismissing tried and true ideas as the better generalization.

Renaming or redefining “tests” because the LLM gets confused by the word is the tell.

You use a static typed language for guardrails but then you throw out the guardrails of a database schema? Seems like those two decisions are directly at odds.

Without a db schema, you still have to worry about migrating data at runtime or otherwise. Removing the schema just shifts the pain doesn’t remove it, in my experience.

Not endorsing conspiracy theories but one of the YC guys is an investor in flock, which is positioned to benefit from some of the recent political policies.

The post you have commented on is not pertaining to a general set of skills at all. Its a link to a specification for skills.

Also in a recent interview he implied that anyone who disagrees is an “effing idiot”

> First let’s talk about my credentials and qualifications for this post. My next-door neighbor Marv has a fat squirrel that runs up to his sliding-glass door every morning, waiting to be fed.

Some of the writings here feels a little incoherent. The article implies progress will be exponential as matter of fact but we will be lucky to maintain linear progress or even avoid regressing.

> The vehicle remained stopped, moved to the side of the road

How do you remain stopped but also move to the side of the road? Thats a contradiction. Just like Cruise.

Have you looked into https://maartengr.github.io/BERTopic/index.html ?

This is just sub agents, built into Claude. You don’t need 300,000 line tmux abstractions written in go. You just tell Claude to do work in parallel with background sub agents. It helps to have a file for handing off the prompt, tracking progress, and reporting back. I also recommend constraining agents to their own worktrees. I am writing down the pattern here https://workforest.space while nearly everyone is building orchestrators i also noticed claude is already the best orchestrator for claude.

I use it, sponsor it, and did a small pr. One of its goals is to be the most “forkable” starting point if i recall. But yes its just voice input. It’s meaningfully better than the mac dictation for me.

Anthropic is lucky their credit card processor has not cut them off due to excessive disputes that stem from their non existent support.

This is a really good implementation, but I don’t lean too heavily into skills especially not other people‘s. If I’m doing design who’s to say I want instructions in there in the first place like “pick an extreme“ (instructions in the design skill featured on the homepage)

Like a vibe that activates a certain latent space in the model

This company predicts software development is a dead occupation yet ships a mobile chat UI that appears to be perpetually full of bugs, and has had a number of high profile incidents.

I dislike the idea of coupling my workflow to saas platforms like github or code rabbit. The fact that you still have to create local tools is a selling point for just doing it all “locally”.

I’ve been doing game development and it starts to hallucinate more rapidly when it doesn’t understand things like the direction it placing things or which way the camera is oriented

Gemini models are a little bit better about spatial reasoning, but we’re still not there yet because these models were not designed to do spatial reasoning they were designed to process text

In my development, I also use the ascii matrix technique.

Banning paying users with no warning doesn’t seem super ethical. Probably not unethical, either, but I would not frame them as “the most ethical”

Yep, i have long felt like i randomly get sonnet results despite opus billing. I try to work odd hours and notice better results.

I expect that adding instructions that attempt to undo training produces worse results than not including the overbroad generalization in the training in the first place. I think the author isn’t making a complaint they’re documenting a tradeoff.

For me, I’m simply trying to read the article and there are random full screen pop-ups nagging me to sign up for newsletters and stuff

I have been using an open source program “handy”, it is a cross platform rust tauri app that does speech recognition and handles inputting text into programs. It works by piggybacking off the OS’s text input or copy and paste features.

You could fork this, and shell out to an LLM before finally pasting the response.

I clicked out of the article since it starts out with a contradiction.

Experienced engineers can successfully vibe code? By definition it means not reading the output.

If you’re not reading your output, then why does skill level even matter?

Now roast the horrendous ugly colors on this horrendous ugly website that is frying my eyeballs. Did you prompt your LLM to create the biggest pile of garbage possible? Or is that just how you talk about other peoples work?

Having too many skills can be a mistake. Getting too meta can be a mistake. I wrote about it on my blog too.

Yeah, it’s literally talked about and documented by the vendor as an intended characteristic of the design.

Why is that funny? What company gives you unlimited resources? That doesn’t scale. Google employees can’t just demand a $10,000 workstation. It’s reasonable to assume they have some guardrails, for both financial and stability reasons. Who knows… if it’s unlimited now, will it stay that way forever? Probably unlimited in the same sense as unlimited pto.

I tried this and the flow is sketchy UX even if it’s probably not malicious. It opens Messages, has you send a code to a number they control, and that “verifies” you. Probably to multiplex many chats on one phone number. That’s not a takeover by itself (you’re not forwarding a bank/Apple 2FA), but it’s sketchy. It also doesn’t work. It said hello and stopped replying.

Absolutely, I have worked at several.