Kev
96 posts
Kev
@kev_in_draft
Unpacking my thoughts that are still in progress
Katılım Ekim 2025
73 Takip Edilen24 Takipçiler
@ThePrimeagen I think it’s pretty natural that a lot of us don’t enjoy “hand-programming.” I’ve always loved programming to create endless things but I've always hated having to remember Promise boilerplate, .length vs .length(), and especially in C++ with * vs. ** vs. & vs ->
English
This actually makes me sad. Programming is such a fun thing to do in of itself. The completion of the thing task is the ultimate goal, but the road to get there is enjoyable!
Even as i investigate loops and think deeply about how to deploy AI in a real manner that produces real and good code I still make time for 45 minutes to 3 hours a day trad programming.
But regardless of AI being perfect or not, being able to produce quality work or not is not even part of the argument. I just like programming and I think that loving the craft of building the thing itself will ultimately make the thing you are building better. Because you care deeper about it.
Its not about a pretty dress & lipstick you put on it, but the deep thought care you put in to the things no one sees or perhaps its so good they just don't notice. I think that is where the best software is made.
LaurieWired@lauriewired
I’m convinced that a large % of programmers don’t actually like computers. As a side effect, are also perfectly happy to throw away their reasoning to a model as soon as they can. I don’t get it, at ALL. Don’t you *LIKE* understanding the magic of the machine? You do realize hand-programming (I hate that I even have to specify hand now) is fun…right?
English
@SlowToWrite Not just learn the rules, they should learn sportsmanship. I hate how much of football is just blatant cheating and unsportsmanship.
Im all for Argentina losing, make this world cup more interesting, but man what a horrendous stupid dive.
English
Embolo has hurt Switzerland and helped Argentina. The worst play, so far, in the World Cup. Just a shameless dive by him.
People who blame the ref, including the shameless commentators, should learn the rules.
English
@theoldzealand Spirit of the game? Wtf is the spirit of the game? My guy did the most obvious egregious dive. Thank goodness he got sent off. If anything Spirit of the game should have this happen more often. Send off all the diving players then maybe football's watchable again
English
1/ releasing muse image today — the first image generation model from MSL. it's agentic: pairs with muse spark to reason through your prompt, search the web, and plan before it generates. people get what they meant on the first try. live now in the Meta AI app.
English
@CKCapitalxx So you're going into crwv at $80 for just a 30% gain to $100
English
I wasn’t a massive fan of $CRWV at triple digit prices.
But at $80 a share and a backlog more than double the market cap.
Things are getting interesting.
English
At this point I’m genuinely convinced most of you would have kept reading the assembly code after C got popular
Theo - t3.gg@theo
How much better do the models have to get before you'll stop reading the code?
English
Theoretically you can design an experiment to make this work. Just get stock prices and company documents and news sources from 20 years ago, feed that to a local model and ask it how to run the account for the next 20 years.
The problem is without internet search and determining the data source ourselves actually might be a much bigger nerf to the ai than we would think. Also the fact that it would probably have to be a local model so it won't be using the built in harnesses of top models.
English
wtf ... how do you measure 20 year strategy against llms?
Polymarket@Polymarket
JUST IN: New study reveals LLM-based trading strategies mostly failed to outperform a simple buy-and-hold strategy over 20 years.
English
@KrisPatel99 @TheMoMoDesk Yeah they don't care about financial fundamentals but they're not fully irrational. No one values startups and growth companies on fundamentals either and AI has turned a lot of mature companies back to growth companies.
English
$MU
Next year growth rate will be 72% then the year after that 5.6%...
If your buying today, your buying a business that is going to slow down by a lot in the next 2 years.
The market is forward looking.
$MU isnt not a GROWTH company. They are a cyclical business that near peak growth rate.
The air pocket between growth to value compresses multiples. Share repurchases can keep the stock up for the time being but longer term, this thing will come down ALOT.
Just cant tell you when that is. Keep dancing but listen for the music slowing.
The upside from here is like 10 to 20%... the downside is 80% lower in the future.
English
This is horrendous advice. You just have to think for yourself snd your own investments why did you initially go into $NOW? Did anything change for your thesis when it went up? Whats your 5 year price target? It All depends on these. If you have high conviction that it will 5x or 10x or whatever in 5 years why would you sell for only 30% up? Now if you thought it will only be up 50% in 5 years then you probably should have sold. Or even double in 5 years, 30% up in a few days would have been decent profits. But you can't just blindly follow shit advice like this, you can't perfectly time the markets for 30% up and downs if you believe in substantially more returns.
English
@IndexAndForget Yeah I’m new to all this sort of stuff bro and I see everyone say hold on during the dips and what not so just trying to stay disciplined at the moment really
English
@willreil If the waterloo, Mcgill and UOFT Alumni in the U.S. pooled their networths together, they might straight up be able to buy the whole Canadian tech sector.
English
We're actually starting to re-invent programming languages
Michael Thiessen@MichaelThiessen
I’m so sick of Markdown right now. It’s amazing for humans and LLMs, but impossible to process or manipulate otherwise. Is there anything that renders like Markdown (for humans) but has a strict structure (like XML/YAML/etc) so it’s easy to manipulate? Ideally, a superset of Markdown, so it “just works” and renders like normal Markdown. But with added structure that makes it easy to parse and verify and manipulate. I’m building my own thing currently but I’d rather not.
English
@cursor_ai @PaperGainsInc direct competitor to what you mentioned about $MSFT today lol
English
We're launching code storage and git hosting.
Origin gives teams and agents a place to host, review, and collaborate on code.
Available this fall. Join the waitlist.
cursor.com/origin-waitlist
English
5 mins to explain the task sounds way too little. I think the problem is honestly human error. Because models can create great MVPs / PoCs we're often tempted to just iterate on that PoC for hours. Meanwhile your initial 5 min explanation was probably not good enough for anything tangible.
We should let the POC be a POC and just start completely over. The 13 hours is honedtly probably a fine amount of time for us to refine our plan and what we actually want to build.
English
Typical coding day with Claude (Opus 4.8)
- explain to Claude the task (5 minutes)
- Claude implements task (10 minutes)
me: "Why is this necessary?"
Claude: "You're right to push back! I over-engineered this!"
- Repeat x87 times (13 hours)
English
@stevenfiorillo @claudeai Even more pressing question, if fable 5 doesn't come back do you not see this as a serious issue to the AI market? Heck even if it does come back isn't this back and forth with the government already a major risk for AI?
English
In all seriousness when is Fable 5 coming back? I thought Opus 4.8 was great until I used Fable then it got taken away. @claudeai any updates would be great.
How many people noticed a huge difference between Opus 4.8 and Fable 5?
English
@haydendevs Love how this whole thread just proves the point lol. I still don't get what people are personally using agents for.
English
@yacineMTB I've been wondering why none of the finance bros are more up in arms about this. This makes it really awkward for all the research labs cause model bad -> no one wants to use but model good -> government takes away.
English
Why are there little to no finance bros on X talking about this. This should be a huge deal in the investment world.
Anthropic@AnthropicAI
The US government, citing national security authorities, has issued an export control directive to suspend all access to Fable 5 and Mythos 5 by any foreign national, whether inside or outside the United States, including foreign national Anthropic employees. The net effect of this order is that we must abruptly disable Fable 5 and Mythos 5 for all our customers to ensure compliance. Access to all other Claude models is not affected. We apologize for this disruption to our customers. We believe this is a misunderstanding and are working to restore access as soon as possible. Read our full statement: anthropic.com/news/fable-myt…
English
@stocktalkweekly 😂😂 sounds like a win win though, strait opened and get them bag holding
English
*IRAN AGREES TO OPEN STRAIT OF HORMUZ IN RETURN FOR SPACEX IPO ALLOCATION
English