dcchuck

In one of the earlier iterations of this they at least made the UX distinguish Codex vs. ChatGPT which I really enjoyed.

I must admit I spent a little time in ChatGPT this weekend, thinking I was in Codex. After some unexpected behavior (disappointed) I realized my mistake.

Bertrand Russell wrote a text which touches on this exact subject, The Conquest of Happiness [1].

Ignore the hyperbole of the "who should read it". In my opinion, it is his thoughts on happiness from his own life. Some of it is dated, but I found it a relaxing and rational take on the topic.

[1] https://www.amazon.com/Conquest-Happiness-Bertrand-Russell/d...

Yes - presuming the funds can’t earn SOFR+. The opportunity cost is the interest being earned elsewhere (minus interest earned taxes)

Curious what others use to store media for home/remote use.

I naively assumed my purchases from [company A] would mean I have permanent/immutable access. Even in the case of access not being revoked, I've found content itself changes over time. Usually related to jokes which have "not aged well" let us say.

I'm not here to champion leaving in that content. Or defend nostalgic rewatching. It just feels strange to not acknowledge.

Our team calls this "full three pepper blend" ;)

Same

This is great! Thank you :heart:

I enjoyed the sentiment, thank you for sharing.

Came to post about the site. My first reaction to the layout was "Oh, must be optimized for mobile." Then I clicked a link in one of the articles and it opened alongside it. Very slick. I enjoy this! It enables that "wiki deep dive" style of browsing. I suddenly want to read all your notes.

Hot Take: best $5k you've ever spent.

Imagine living your whole life thinking you couldn't do it?

I'm not saying it's fun. Just saying it may be a good thing.

I agree. We skipped CLIs and went all the way to TUIs because TUIs are "easy to make now"? Or maybe because claude/codex?

But in practice you are padding token counts of agents reading streams of TUIs instead of leveraging standard unix pipes that have been around from day 1.

TLDR - your agent wants a CLI anyway.

Disclaimer: still a cool project and thank you to the author for sharing.

I agree. The first paragraph on the page implies the javascript can natively search your machine (vs. via Browser Extensions)

Yes exactly.

The problem is TUIs. Or at least the assumption you're only supposed to use a TUI. There are plaintext ways to invoke things but the advertised Claude/Codex experience is a TUI. You can't pipe the contents because it's not next - it's instructions to draw to the terminal.

<humor>TUIs are the new podcast! With everyone asking you to invoke tools via a TUI, there was nobody left to write actual tools.</humor>

TLDR - make sure you support plain text too ;)

This is a github pages feature. Given an account with the name "example", they can publish static pages to example.github.io

So this being from github.github.io implies it's published by the "github" account on github.

I prefer all my custom commands as 1 letter.

On my most frequently used machine/dev env this means -

e for vim

m for mise

n for pnpm

c for Claude

x for codex

I was excited for actions because it was “next to” my source code.

I (tend to) complain about actions because I use them.

Open to someone telling me there is a perfect solution out there. But today my actions fixes were not actions related. Just maintenance.

Couldn't agree more.

I would expect older models make you feel this way.

* Agents not trying to do the impossible (or not being an "over eager people pleaser" as it has been described) has significantly improved over the past few months. No wonder the older models fail.

* "Garbage in, garbage out" - yes, exactly ;)

I find myself using VS Code for "things like this" (its visual extension ecosystem).

I've grown attached to the git diff view, so I use it for reviewing PRs mostly (especially larger ones as github UI has been struggling with them as of late).

The rest of my code is written in Vim or by Claude.

I spent some time last night "over iterating" on a plan to do some refactoring in a large codebase.

I created the original plan with a very specific ask - create an abstraction to remove some tight coupling. Small problem that had a big surface area. The planning/brainstorming was great and I like the plan we came up with.

I then tried to use a prompt like OP's to improve it (as I said, large surface area so I wanted to review it) - "Please review PLAN_DOC.md - is it a comprehensive plan for this project?". I'd run it -> get feedback -> give it back to Claude to improve the plan.

I (naively perhaps) expected this process to converge to a "perfect plan". At this point I think of it more like a probability tree where there's a chance of improving the plan, but a non-zero chance of getting off the rails. And once you go off the rails, you only veer further and further from the truth.

There are certainly problems where "throwing compute" at it and continuing to iterate with an LLM will work great. I would expect those to have firm success criteria. Providing definitions of quality would significantly improve the output here as well (or decrease the probability of going off the rails I suppose). Otherwise Claude will confuse quality like we see here.

Shout out OP for sharing their work and moving us forward.

There's a Bertrand Russell book on this very topic, The Conquest of Happiness - https://www.amazon.com/Conquest-Happiness-Bertrand-Russell/d... (not an affiliate link)

I enjoyed the read. Felt like Russell just thought about this question for a while, and shared his thoughts. It was very practical and enjoyable.

Disclaimer: I recall some "wow, we don't talk like that anymore" moments. And I didn't enjoy the hyperbole of the cover quotes. But the content of the book debunks those.

Yes, but image size restrictions bring more failure than success in my experience.

Thank you for your comment.

My experience with the off the shelf MCP tools is they still fall short of giving Claude or Codex a screenshot.

I'm interested in whether or not others agree.

This is the type of romcom I'd watch ;)

Gartner stock price:

On the day this was published (2025-02-07) it closed at $529.29. Yesterday it closed at $238.37.

Source - https://finance.yahoo.com/quote/IT/history/

Victory lap submission?

This appears to be another take on a previously discussed study

One discussion - https://news.ycombinator.com/item?id=44549436

Congratulations to the Figma team! Well earned. It was such an exciting product when it hit the scene. It became the standard so fast, and it was easy to see why. When there were talks of them being bought for $20 billion I thought it was a great deal for Adobe - and that was before seeing these impressive financials.

I will admit I have waned enthusiasm a on Figma over the past couple of years. I find the UI churn confusing. The new features, i.e. dev mode and variables, feel out of place. I find the plugin ecosystem cumbersome. Doing simple things has become complex. I'm putting out real "who moved my cheese?" energy here I know. I suppose I'm wondering if others feel the same.

Really? I must admit I have not noticed it. I've had nightmare trips trying to get into the city still during traditional heavy traffic times. Frankly I've thought more "the pandemic is finally over" than I did "congestion pricing is working" over the past few months.

I'll be curious what happens come winter time. Midtown becomes gridlock in the evenings. I do not expect that to change.

All that being said - probably my own biases skewing things. I will keep my eyes peeled!

I actually paid for tax advice from one of those big companies (it was recommended - last time I will take that person's recommendations!). I was very disappointed in the service. It felt like the person I was speaking to on the phone would have been better of just echoing the request into AI. So I did just that as I waited on the line. I found the answer and the tax expert "confirmed" it.

I agree! Real "Fear is the mind killer vibes"

Thank you for sharing. I particularly enjoyed the call out where you highlight what you learned from the incident. Took the post from fear-brain to information-brain for me (don't mind my curiosity haha).

I had a much less intrusive incident but equally "alarming" ;). The apartment I live in has hard wired smoke/carbon monoxide alarms (with backup battery). One night, ~2am 1 of them starts beeping that the battery is dead. I confirm the breaker didn't flip or anything...finally decided to complete disassemble it and get some sleep. 4 of these in the apartment. Head hits the pillow and a second one goes off! Take all 4 down and live dangerously for an evening.

In the morning I do my research - turns out these things just start doing that after 10 years. "Get a new one!" it peeps incessantly.

Shame me please - as I bought replacements. I'll save this post for myself in 10 years so at least I can be the one to say "I told you so".

Came here to share that same experience. RStudio truly made me feel "close" to the data.