@fastidiousprofilefollow"Beware those that would deny you access to information, for in their heart they dream themselves your master." โ Sid Meyerswrote:
Maybe implementing a subset of Markdown would be a good thing. I am thinking about bold, italics, inline code, and code block, mostly. Oh, and links.
I agree that minimalism is hard. Thatโs why the subset was explicitly recommended small. Yet, I believe it is extremely useful to have.
@fastidiousprofilefollow"Beware those that would deny you access to information, for in their heart they dream themselves your master." โ Sid Meyerscontinued:
I've tested MD and honestly I don't like it. Bold/italics add unnecessary noise/clutter and the font is already monospace, suited for code, so inline code & code fences are not needed. If 3rd party clients want to implement them it's fine but I'm sensitive to visual noise.
I agree with this. The core you're building is around a deliberate minimalist philosophy. I was happy to build an opinionated client for my own use-case, but it should imo stay on the fringes for those seeking it.
Asked Claude to implement a game based on a text quest book I played in 90s. Letโs see. Tried to play the original text, downloaded epub. Well, I died after 3 minutes in the game.
#Emacsnotesfollowโ keybindings are easy and the best out there, they are mnemonic.
C-c k p l - kubernetes-pods-list
M-g n - go next
C-h v - help on variable
M-s o - search occurrence
@thechelsukprofilefollowCurrently in remission from ME/CFS after 3+ years. Occasional software engineering leader, app developer, blogger, zwifter, and just being online.wrote:
@thechelsukprofilefollowCurrently in remission from ME/CFS after 3+ years. Occasional software engineering leader, app developer, blogger, zwifter, and just being online.wrote:
@elana๐งprofilefollowI have a doctorate in ancient stuff but these days I'm a full-time plague avoider. Born and raised in Toronto, Canada, now living in Kyoto, Japan.wrote:
The essence of aligning large LLM models is basically to conform to the existing social order. ChatGPT respects China's order, while China's open-source models, although reluctantly, also tolerate the order in the US. Maybe we can build a revisionist SFT dataset.
This may become a thing. Have you seen the results of PISA? School performance is going down in the OCDE and richer students are going down faster (they have more tech available). Maybe the future si for those who ditch the computers.
When I was 10, I thought I'd be a scientist
I wanted to tinker in a lab, doing something with beakers and bunsen burners
Making a difference.
As an adult, I sit in meetings and discuss who to fire next
I tinker with spreadsheets, doing something with LLMs and JIRA
Be enthusiastic
#poemnotesfollow#aifearnotesfollow
As young kid I dreamed of working with reel-to-reel machines
Cutting/splicing tape, happy accidents
As a teen I couldn't afford reel-to-reel but got decent with multi-track cassettes
Everyone was telling me digital was The Way (tm)
In my 30s, I finally learned how to use a DAW properly
In my 40s, I'm back to playing around with multi-tracks cassettes
There is no money in it, but I'm enthusiastic as I can be
(this is not so much as direct response as simply a response)
#musicnotesfollow#aifearnotesfollow
Is open source dead?
Everyone has the power now to make their own stacks of things.
The people aspect of open source is dead or dying. I don't think the bunny is going back in the box.
One nice thing about Open Source (at least for me) is different people doing the same thing in different ways and one of those happen to suit my taste perfectly. And in many cases, I won't be able to come with it myself even with Super Intelligence.
Evgeny Morozov has pointed out that using ai through chat interfaces is based on an individualised and privatised model, which (heavily paraphrased) is inherently anti-social.
With an extra layer now of people making small personalised tools, do bigger things still need teams of people who know what theyโre doing?
FWIW Iโd like to see more sharing of vibe coded tools instead of everyone making their own more less the same ones. Mine are here: pauladams.neocities.org
I don't think so. I have been using more open source software than ever before.
You may argue that with LLMs I have the power to make my own stack of things, but this doesn't eliminate that I still need knowledge to properly steer an LLM to create something worthwhile.
If I have no knowledge of what I intend to build, the best thing the LLM will generate is a half-assed copy of something that already exists. Which is what we have been drowning in the past couple of years.
AI can be a superpower in the hands of someone knowledgeable. That makes the people aspect of open source more important, not less.
If you offload your curiosity and desire to learn to AI, you will be a slave to it's limitations instead of being a master of its capabilities.
Of course not. I think it is much more relevant to ask "Is closed source dead?".
Anyone can now replace a proprietary program with a vibeslopped alternative which might suit them just as well. It will have the same level of trust (ie. none) and none of the other drawbacks.