Live data from Hacker News

Codex-maxxing

jxnl.co

71–80 of 90 posts

Re: Codex-maxxing

#71

Is this LLM psychosis? So much tending and conversing with the matmuls but what was the outcome? Are people who get this into it more successful somehow? It reminds me of people who take drugs and get "revelations" but then are not particularly over represented in the group of successful people for all of their deep insights.

Calling something emergent a matmul is like calling a human an axon discharge.

Re: Codex-maxxing

#72

I'm trying to get out of this. I'm a blind person. No one in tech goes to bed thinking about us, as it were. So, as a non-programmer, vibe coding accessibility fixes was an outlet to the daily million papercuts of using operating systems built by people who cannot understand me. Well, I have barely anything to show for months of this. I made Termux more accessible on Android, made an MUD client for Emacs, fixed up so…

How does a blind person read and write code? Serious question. I’m imagining braille screens (is that a thing?)

Re: Codex-maxxing

#74

Is this LLM psychosis? So much tending and conversing with the matmuls but what was the outcome? Are people who get this into it more successful somehow? It reminds me of people who take drugs and get "revelations" but then are not particularly over represented in the group of successful people for all of their deep insights.

> It reminds me of people who take drugs and get "revelations" but then are not particularly over represented in the group of successful people for all of their deep insights. This depends on where you're looking for "successful" people. I generally agree with you - of those people who might report "revelations" through hallucinogenic drugs, the majority may misinterpret their drug-induced experience and hence be mor…

LLMs vs psychedelics are an interesting comparison: psychedelics lower the threshold for the epiphany sensation, arguably LLMs do the same through agreement (‘sycophancy’).

With psychedelics you see the upsides in engineers who come to work the next day with designs informed by massive insights, and the downsides in people whose ‘massive insights’ result in socially abnormal behaviours.

LLMs seemingly provide validation and support, something very lacking in most lives. The distance between thinking loosely about, say, an app and getting positive feedback and absurd market predictions triggers similar ‘revelations’ in people with no meaningful context, and plays on the hopes of those who do. Much like with psychedelics, though, there is a self-supported self-validated cycle going on, prone to flights of excess.

Re: Codex-maxxing

#75

I'm trying to get out of this. I'm a blind person. No one in tech goes to bed thinking about us, as it were. So, as a non-programmer, vibe coding accessibility fixes was an outlet to the daily million papercuts of using operating systems built by people who cannot understand me. Well, I have barely anything to show for months of this. I made Termux more accessible on Android, made an MUD client for Emacs, fixed up so…

How does a blind person read and write code? Serious question. I’m imagining braille screens (is that a thing?)

screen readers

Re: Codex-maxxing

#76
post #44
post #21

Earlier quoted context omitted.

same author who's idea of constraint decoding for structured outputs was to run an schema-begging-API call in a loop 10 times & then throw an exception on failure.

source?

https://github.com/567-labs/instructor/blob/main/instructor/...

Re: Codex-maxxing

#77
post #65
post #3

Most people I know underutilize voice mode. Such a game changer for making brain dumps the LLM can just gobble up

I hear a lot of praises. Can you explain? If I can type as fast as I speak, does that still matter in such case? Does it make use of intonation or is it pure speech to text?

For me it's because I've been walking 10-20k steps per day on a walking pad at my standing desk while working.

I can still type while doing it but it's so nice to just hold a button (or double tap to lock recording) and just brain dump what I need.

I type very fast but I feel like the unaltered speech to text allows me to express more quickly any uncertainty or doubt that I have or when I don't know exactly how to best ask for what I want.

I also like to play dumb with agents and ask it for the best option for something that I already know the answer to, just to see if it's gonna be correct, it helps get a sense of the limits of each model. That's also quicker on voice.

I don't think it makes use of intonation for the built in one, I use Hex on mac for speech to text

By this pretty cool dude -> https://github.com/kitlangton/Hex

Re: Codex-maxxing

#78

Earlier quoted context omitted.

Still not useful enough for me and I really want this feature! The problem I encounter is the inability of the LLM to look stuff up and respond to me. "What's that name of that database table?" "What are all the services that call this endpoint?" "Are there any open PRs for this repo right now?" Once information can flow in both directions not just one it will be a gamechanger for me.

This works today right? What part of this are you missing?

Not as far as I know. Can you walk me through the process?

I have my phone, I'm going for a walk, what app am I opening?

Re: Codex-maxxing

#79

Is this LLM psychosis? So much tending and conversing with the matmuls but what was the outcome? Are people who get this into it more successful somehow? It reminds me of people who take drugs and get "revelations" but then are not particularly over represented in the group of successful people for all of their deep insights.

> It reminds me of people who take drugs and get "revelations" but then are not particularly over represented in the group of successful people for all of their deep insights. This depends on where you're looking for "successful" people. I generally agree with you - of those people who might report "revelations" through hallucinogenic drugs, the majority may misinterpret their drug-induced experience and hence be mor…

Coming out publicly about doing drugs is just not something that smart people usually do.

There's a lot of stigma about it and a lot of opinionated people who don't know anything about them and still have a lot of judgements.

Then there are these people calling psychedelics hallucinogens. The former can give spiritual revelations and the latter gives vividly realistic, usually nightmarish, hallucinations.

There are also people putting an equal sign between crack cocaine and psylocibine mushrooms. But I don't think an addict will rob a petrol station with a screwdriver just to get another dose of magic mushrooms.

In such surroundings, it's just not a good idea to publicly say anything about drugs, unless you're so rich or known for your expertise, that you can shoulder some negative judgement and it's implications.

Re: Codex-maxxing

#80

Earlier quoted context omitted.

This works today right? What part of this are you missing?

Not as far as I know. Can you walk me through the process? I have my phone, I'm going for a walk, what app am I opening?

For Codex, that is ChatGPT? https://openai.com/index/work-with-codex-from-anywhere/

Or do you want it to speak to you too? I think this would have to be TTS on your phone. You can have ChatGPT speak to you but I don't see that feature in Codex.

Post reply on HN