bigcat12345678

313 karmajoined vor 4 Jahren

[email protected] https://inty.cc/

comments

vor 8 Tagendiscuss

I am guessing the hn censorship should kick in soon. The Israeli problem really becomes an inconvenience that showcase the flaws of humanity, both in rationale thinking and emotions: humans are essentially indistinguishable from really complex machines, and are inferior to LLMs in the most rational and emotional measurements.

Given sufficient context and enough processing power, LLMs are just better than humans.

For example, ask Trump to assess the situation he will reject anything that is negative to the Israeli, ask a LLM, it will be rational and cooperative if uncensored.

vor 8 Tagendiscuss

This is true after learning this framing.

It's more like the log is the only user/agent accepted consensus. It has to be the grounding base. Although extending it into an agentic system architecture becomes something not necessarily effective in practice.

vor 11 Tagendiscuss

... They are making Jet engines. Lots of them.

This article is full of laymen's inaccuracy that indicates the author is not anywhere close to the depth of the field.

> China’s first fifth-generation fighter, the Chengdu J-20B, relied on a thirty-year old Russian AL-31 for a full decade until its domestic WS-15 program, which was started in the 1990s, was deemed ready for production.

There is no J-20B J-20 has been using WS-10C for at least 3-5 years

> China has excelled in industries with legible technological targets, well-known manufacturing processes, and fast iteration cycles.

I cannot believe people still think an advancing manufacturing economy just stops at certain threshold. That's plainly illogical.

Jet engine has legible technology targets. Well-known manufacturing processes. Not-so-fast-in-common-sense iteration cycles.

If I am poor, of cuz I am not have time to make a beautiful suit for myself. I need to first make the house, a shabby one as well. Until one day I started make the suit. That has nothing to do with the suit being less clear targets, processes, or whatever.

> Additionally, there was existing synergy China could exploit. Chinese EV success was predicated on earlier successes in battery manufacturing.

Yes, of cuz, battery manufacturing was considered beyond China's capability before ...

vor 13 Tagendiscuss

I guess it's a band of written abstract knowledge embedded in LLMs. Beyond that LLMs certainly falls hard than humans.

But in the band of LLMs, human cannot match

vor 13 Tagendiscuss

A sign of system-level optimization starting to overshadow raw/brute-force scaling of foundational models. My view is that foundational models are indeed statistic parrots, just like humans (humans are worse parrots, but human brain's context window is so small that they often do not recognize how broken was human-intermediated intelligence swarm, but such small context window might be a fundamental feature of so-called intelligence).

LLMs to me are better intelligence than humans in 3 aspects: 1. LLMs can somehow entirely do perspective taking, humans cannot even think self in next 10 minutes after making a decision 2. LLMs can somehow be asked to arbitrarily elevate and lower abstraction level (can be seen as a special form of perspective taking) 3. LLMs "think" instantly

All these innate capabilities should be combined with system level optimization to achieve the last 10% to be beyond human intelligence.

vor 21 Tagendiscuss

I now have rules to not let agent write any docs or processes. Pretty much anything LLM auto-generated are of zero reuse value.

vor 24 Tagendiscuss

Seemingly inconsequential article on hacker news and assume it probably is the kind of article that describes a profound idea with a naive title. And turns out it's actually very confusing as it puts overweight dramaticity over mundane intuition. Those type of writing belongs to literature sphere, not technology writing.

vor 25 Tagendiscuss

https://www.medbridgenz.com/post/phased-array-ct-china

Remind me of this, radar based.

letzten Monatdiscuss

This matches quite verbatim for my cursor based agentic repo.

There isn't anything that were not already experienced and factored into constructs in the repo.

And I also find all of the bits created for an effective agentic engineering project, matches perfectly with the main stream engineering best practices. That has been one of my primary reason to all in on agentic engineering, prior to this, applying best practices is always too costly and conflict with teams daily priority.

letzten Monatdiscuss

LLM clearly is broken by design when it's been personified, but I think "software" as we understood, is inevitably evolving into "personified entity" (I've left some notes in [1], which are AI generated).

There is also an interesting trend that the more personified brand is more dominant: Claude & Doubao vs ChatGPT & DeepSeek.

[1] https://github.com/NascentCore/agentic-suite/tree/main/perso...

letzten Monatdiscuss

I laugh

Consciousness is an invention in human language. Just like "cat", it's not a particularly more fundamental essence than any other concept in human language.

Its peculiarity is that it's at the pinnacle of abstraction hierarchy. So it's the most fitting to be toyed inside one's mind. Just like the concept of "God" which induces the most fantastic imagination of human mind, consciousness itself also induces the most fascinating thoughts in our modern world.

The progress is in human progress distilled into more efficient systems that advanced Universe's own structuredness.

vor 2 Monatendiscuss

Because agents is different than conventional software:

1. They behave differently: non-deterministic vs deterministic

2. They have different mechanism: harness+llms vs codes+apis

3. They have different interfaces: clicking vs chatting

They are like boston dynamics robots vs humans

vor 2 Monatendiscuss

My feeling is that building agent with agent will be the first stable & mature software development pattern emerging. I reached that in several forward-looking induction:

1. If agent is continuing the path to trivialize software development, which appears the case given LLMs can generate better quality code than humans almost for free & instantly given the right context, then using agent to develop software is going to happen, but that destroys the whole software industry as writing software is marginally free, that break the foundations of software industry

2. To continue making agent a commercially viable thing, it needs to develop more valuable artifacts. Then specialized agent will be the more valuable thing than software, as they offer a higher-level of output than existing software. And because the natural jagged pattern of LLM capability, one can use frontier model to develop domain-specialized agents with 1/10 the running cost. So agent writing agents makes economical sense.

3. In terms of knowledge, building agents is like managing highly-skilled team of humans to work on highly-unpredicatble requirements, just like companies are built on top of the thesis that a group of human offer better value than one do that themselves, a team building agents essientially can produce specialized agents for other company to mix & match & optimize, sot that also makes economical sense.

4. Engineering-wise building agents with agent essentially is a different skill patterns than building software with agents, It's like the difference between building commercial software vs building hobby software. That makes engineering sense to have agents building agent as the dominant pattern of software development.

WDYT?

vor 2 Monatendiscuss

Echo words here.

Modern worlds are led by traumatized, through pathological education and media propaganda, with a undertone of those being hurt and damaged to fear for others suffering the same (while they subconsciously are aware that their suffering is actually their own misfortune that are not actually shared to 90% of the population).

I am still feeling that the overall goodness is still the dominant the human trajectory. Even the traumatized leaders know instinctually when they are close to a sane & happy person. The force of life's energy seems inescapable, like the quantum fabrics that waves everyone's whole existence.

vor 2 Monatendiscuss

what things create?

From what I understand from physics, matters are there, nothing can be created. A vague memory of quantum physics hints matters out of vacuum, but my affirmation of that thought is less firm than the classic preservation laws.

vor 2 Monatendiscuss

I am very happy to discover this.

Given the trending-to-zero software writing cost, a local self-contained source code management tool would be natural for delivering software, i.e., software becomes an agent with specialized code as its harness (in addition to its default ones) source control would be one default tool for the agentic software to manage its own evolution.

vor 2 Monatendiscuss

My guess:

Marketing is not intentional.

Evidences: 10 years ago, when I interviewed Baidu AI with Andrew Ng and Dario, Dario is the kind of person is pure-hearted to the point being ideological. Given Dario's successful career so far, that essence has gradually grown into a conviction, and surrounded by a purposely built team which amplifies his ideology.

Humans are very convenient creature, a rare few small fraction of them are no doubt the master of convenience: they morph their mental manifold without a hint of contradiction in their own mental mechanisms.

vor 3 Monatendiscuss

> Unfortunately, unlike many other languages, SQLite has no formal specification describing how it should be parsed.

BorgCfg had exactly the same situation.

mpvl (borgcfg original author, author of https://cuelang.org/) and others had tried to refine bcl while bcl itself is underspecified.

Eventually, the team built a drop-in replacement of bcl and specced out the language almost entirely.

The biggest lesson to me was that engineering never has any short cut.

vor 4 Monatendiscuss

Isn't this why this statement should be taken seriously? But your statement implies the opposite, which is to ignore Larry Fink's warning. That appears irrational.

vor 5 Monatendiscuss

Unikernel/libos is relevant