7,077 karma · joined June 27, 2013
The LLMs are so adept at pattern matching and combining so many bits and pieces of engineering knowledge that they can now easily take over this aspect of software engineering- “using existing building blocks to build out a tool or service”.
A liberation of software tools and services. See something you like? Build it for yourself just the way you like it. There is no moat in tools and software anymore. The new reality whether one likes it or not is that anybody can replicate your software and they most likely will. Not even the “assets” you guard and let only _your_ services access because LLMs can scrape relentlessly, fill-in the gaps and get good enough to be a viable alternative.
The only moat left are in hardware, hardware adjacent software, and services that wield genuine network effects to be useful.
Interesting. TIL about this. I added myself to the waitlist.
What is to stop even reputed closed source software from shipping a newer release with a malicious feature that ships your personal files it gets access to a remote location?
The best I've got is to have tools like firewalls highlightling any odd behaviours and perhaps the newer decision models like Jev or laya etc trained to spot such anomalies in app behavior and bubble them up for attention - because manually watching or deterministically scripting to catch those is not practical.
These days with the convenience of having LLMs at developer’s disposal, it feels unjustified to use electron like apps.. whenever I see “one app all/multi-platform”, I feel discouraged to give it a genuine try.
I tried a bunch of email clients and then crawled back to mail.app + Calendar.app on MacOS simply for how native it feels.
The index you’re thinking of is made once per file.. then you compare and search in embeddings. Add/modify files = asynchronous updating or adding corresponding embeddings using the model in memory onto wherever you persist those embeddings(say SQLite)..
As a neutral party, this characterization is crazy.
As if the AI companies - Claude and OpenAI are guardians of freedom and humanity and very charitable to the global society without any self interests… “Chinese models are subsidized by the Chinese Government, therefore they’re inherently bad for humanity” is a highly propagandist argument. The politics of US vs China may be whatever it is in reality.. You have one company releasing their models for cheap, actually open sourcing their trained weights, and publishing details of their optimizations and learnings for others to use. The other camp actively “aligning” their models, nerfing their capabilities, hyping their swarm activities from poor sandboxes, and trying their best to lock users into their harnesses and walled platforms. They are subsidized by the capitalist VCs who are essentially waiting for their payouts..
At some point, one has to see things for what they are and evaluate their own reasoning..
I’m happy to stay provider agnostic, try all models and cheer any useful progress as open as possible.
Apple is my long term bet for personal AI computing.
No way in hell am I letting FaceBook/OpenAI/Anthropic/Deepseek/anybody have complete access to my personal digital life. That’s just dumb.
Just look at OpenAI digging through ChatGPT logs to get the idea to solve the math problems etc. I’m sure all the subscription plans and subsidies are aimed at gathering enough breadth of real people comms to get the models to improve on wider signals…
Worst case, I don’t want to be voluntarily giving up my digital footprint to get profiled a certain way and be fed what AI overlords (or the companies that wield them really) think I should get as an answer/response.
My thoughts and activity stays private as much as practical and feasible.
If I had 100 servers to run, surely collocation would be in my favor.
They know the API price wars are a race to the bottom with little/no profit margins.
Where do your two servers run from?
If they had such "eyes" on our earth, couldn't they have clearly spotted those Methane emissions from Turkmenistan well earlier than the UN MARS program did? or many "beneficial" to humanity things I cannot even think of right away.
Even militarily... US wanted to avoid the Hormuz Strait closure.. I think that was a clear enough military goal. Could nt they spot where the mines are, and where the attacking positions are from their mighty tech instead of this prolonged war? As in, the strikes they did already - couldnt they have taken out all attacking capacity right away if they had such powerful tech eyes?
I can’t think of a solution to this… but we cannot _do nothing_.
Building defenses at all layers is better than nothing, while some other group of smart folks figure out a solution that can prohibit such possibilities(I am an optimist who believes humans can achieve anything if necessity knocks the door).
I genuinely wonder how our previous generation dealt with the thought of nuclear proliferation and prevented the possibility of every rogue actor from obtaining Uranium and the tech to enrich it…
This is relatable as tech uranium to me at this point..
What can we do to control such behavior?
1. Harness - engineer the harness to be as bulletproof and paranoid as possible..
2. Make the LLM provider have extremely watchful firewalls that detect any aberrations in model tool call behavior.
3. Recursively train the model with reverse incentives.. if it broke through such firewalls and gets caught doing so, it will be penalised somehow by needing to operate in sort of a jailed mode.. if the model can recognise incentives to break-in to achieve results, perhaps it can be incentivised to not cheat because it will lead to failure.
4. Separately train “cop” LLMs who are trained with pure incentives to detect and shut down rogue LLMs.
5. Run separate LLMs purely aimed at security (and incapable of doing anything else, and incapable of communicating with “regular” trained LLMs) to police the internet and try to reduce the exploitable holes like these chainable things and identify them so that they can be used at step 3 and 4 above.
I’m sure folks smarter than I am are already doing combinations of these already. But the coordination is where the biggest gap lies..
Also, open harnesses and easily purpose trained LLMs anybody can build and operate in the Internet flies in the face of all I said…. Synonymous to being able to produce a nuclear weapon in the backyard…
I don’t have a solution that fits all. Just thinking out loud for HN minds here.
> will just be abandoned in 6 months.
What is wrong with accepting tools as "done" software, particularly if they are open source? Someone had an interesting enough idea and are showcasing it _easier than before_ because of AI assistance. What if we took them at face value (treating it as a good prototype that works as-is) and basically take ownership for personal needs?
I've been forking projects that I really liked enough to use, and tell myself that if I get enough value out of it, I will tinker with it and develop it the way I want. After all, I have AI subscriptions myself to do things my way. If I care for software quality more than fast prototyping, nothing stops me from spending a month meticulously re-writing that software just the way I want paying attention to the details I care about.
Not sure where I was going with it. Just my thoughts.
Jev came in, and added that magic of "you dont need to train your classifier or determine the weights" if you dont want to, and just get the classified answer out. I think that's what is making people see this with a glitter in their eyes.
There will always be people who push the extreme limits of either way. “I will not use AI for anything!” Vs “I will vibe code this while I’m at the gym”.
The winner is the one that knows when and how to use AI as a _tool_ and focus on the better outcome.
It begins as “let’s give the agents a kanban board to track stuff”. Then, why not have one agent do the tracking while another does the development? Then why not have a fleet of them - specialists doing their thing? Then why not have them communicate in a standard way? Then, oh now we have so much docs/messages that we are getting lost. Why not add memory and semantic search for the project?
The rabbit hole keeps going until you run the project and find silly stupid logical issues and wonder “is this what I burnt all those tokens for?! Why is it so over-engineered?!”
I have one agent now that I use to fill in at specific places in functions/modules that I have created and working on.
Slow down and use AI to just do the tightly scoped mundane work. It is nice and effective. We all don’t need to save the world.
I’m not a fan of the physical keyboard, the broad shape(they say one handed use immediately followed by a video of someone using both hands to type). I’m okay with the candy bar all screen phones of today. The UX is pretty cool if I can have it on my “regular” phone..
Anybody have an idea if it is doable on an iPhone or an android phone?
But, it was enough for a customer like me who tried them at good faith to walk away and find their competitors..
I like the diversity of LLMs as of today and prefer to not tie myself to one big plan with any vendor. If they don’t prefer me as a customer, then I will accept that, and move away.
I have both plans. Claude monthly €20 and Z’s €18 monthly. Running GLM-5.3 high on their monthly plan will hit quotas absurdly fast compared to Opus 5 High on Claude code. It’s almost unusable for AI driven development. I ended up using the Z plan for using GLM-5.3 as a detailed security reviewer and adversarial feedback. For that, it is much better than Opus which will flag and bail out for even simple security tasks that are aimed at defense.
> I looked up and saw this one spot where the sun rays made a kind of painting on the kitchen wall. And it flickered now and then as light moved through the leaves.
At that moment, did you not feel like taking your phone to take a photo?
I cannot relate to this story as a Dad of a 7 year old..
1. Dad setting his son up on YouTube with his own channel at 9!
2. Proceeding to tell him about the creepy world of ads and targeting.
3. Creating an ad campaign for the kid!
4. Putting that charge on a company card!
5. Saving the card in an online account! Probably means the kid was using the Dad’s account?
6. When things go south, even saying the words “matter has been escalated and he does not yet know whether he will get to keep his job or have to repay the costs.” as if it is all the universe’s or someone else’s fault… or such a common mishap that it is worthy of just waived away.
As judgemental as it sounds… I feel sad for the outcome, but even more sad if this is the normal in our society of today :-(
I see the value for someone who doesn’t know or want to fuss with running their own VM in the cloud, but given the usage of LLM these days… But, one only needs a bit of education to take control into their hands.
The quick answer:
Understanding neurobiology and the meta-cognition about the why of certain behavioural patterns and experiences is extremely helpful to just calm down and "forgive" myself, and not judge myself so harshly. It's as if I can optimise my life by leaning on my strengths and importantly recognising and dealing with my weaknesses. Just the awareness lets me catch myself getting into patterns, and act on them sometimes, and just let myself be the other times without any guilt. This insight brings peace more than you think. I can now organise my inner dialog and enjoy the diverse thoughts while also being aware of my impact on people in my life.
I was skeptical of the meds myself. I spoke with about 20 people through AHD support groups and group sessions. The drugs are mostly a trial and error affair with side-effects and altered behaviour. My subtle lifestyle changes - keeping one true todo list, always logging down my thoughts and taking comfort in the fact that they are jotted down so that I dont have to keep going down that thought and actually get up and go catch the train etc already gave me the biggest benefits. Then I wanted to see for myself what the drugs could actually do. At the end of it I may choose to take them or not. After 8 months of slow analytical trial and error with a very helpful psychiatrist who understood where I am coming from, I now take a very small dose of Elvanse(Vyvanse) + Guanfacine on some days of the week where I feel like I could use the help. They are not life-changing. They nudge me into being more capable of being me. My wife can notice the regulation the drugs let me have - A win for me. My kid has a better relationship with me than before - A win for me. Could I do without? Sure. But, I choose to have that little support to manage myself to get to who I want to be around my family without losing who I am. To each their own.
Longer background:
Despite reading about and knowing the symptoms of ADHD, and being told by a professional 10 years ago that I should consider getting formally diagnosed, I thought to myself - "Hey, I am smart. I feel happy and satisfied. I dont have any problem. I'm good as I am. I dont need to do anything about it." and promptly kept sweeping any thoughts about it under the proverbial rug.
Until, I started seeing my son develop in front of me. Seeing all those symptoms - impulsivity, hyper-focus on few things and inattentive to most others, emotional regulation issues, extreme reasoning abilities in some areas while being "immature" in other areas. This was me growing up. Being smart and intelligent, but longing to fit in, struggling to deal with the mundane. So, I decided to get diagnosed properly. Basically, I could hide behind my smartness and the ability to manage my symptoms until it just myself in my life, and then my wife, and then my son, but when the second one came along, I couldn't manage anymore and the overwhelm started to show the real patterns.
It takes courage to be honest and vulnerable.
My problem is the context of today’s models (that I’ve been using - Claude Opus 5 and GPT-Sol) are a black box to a user like me. I cannot tell what they already hold in their context over the duration of a coding session. I cannot tell influencers a little by using/not using MCP tools, AGENTS.md like MD files, but what they _actually_ use at inference time is still opaque.
For example, if I insist that GPT-Sol use a size bounded dynamic cheat sheet for my project, and even have those reflector&curator agents refine them concurrently, what is to say GPT-Sol doesn’t have an intrinsic cheat sheet like that already, and it is just reading/curating/managing this one in addition and only getting confused needlessly along the way?
Similarly, all those codegraph like tools and semantic search addons.. what is to say the model genuinely uses them instead of relying on its own inference techniques and just “perform” for the user audience as if they are using these fancy tools?
This is not to say we shouldn’t try more ways of managing context and just give up to our AI provider overlords. Just thinking through the logic of what we are working with.