The name "Engram" (n-gram) says it all - this is just another type of statistical word association, not a factual knowledge store.
While DeepSeek describe this as "knowledge lookup", what Engram is really trying to do is separate dynamic reasoning from static pattern recall, with the static patterns just being word-level n-gram statistics, not declarative facts/knowledge.
Just because 2-3 words often appear together in a sequence doesn't mean they represent a fact or truth (or falsehood) - it is just an n-gram statistical regularity.
If Engram helps reduce LLM GPU memory and FLOP requirements then that is great, but it's not a solution for Hallucination.
Foe the ones, like me, who didn't know why you recommended that:
By setting umask 077 first and then creating the file, the file gets created with the correct restrictive permissions (0600) in one step instead leaving the file readable for "everyone" for a moment.
Honestly, the industry is half-torn on whether llms.txt does anything... we're in such a new world. But the same ol' SEO tricks still apply for AI engines for sure.
Haha, yes! Last time I asked it for options how to tackle a task and only do the research without touching any code. With xhigh rasoning, it echoed the options that many times until it was convinced that option A is the better choice and started implementing it.
I found myself in a similar workflow.
Depending on the task at hand (starting a new project, enhancement, maintenance), I let the agent create/read the markdown files that I keep updated (AGENT, STATE, ROADMAP, DESIGN, ARCHITECTURE, (CODESTYLE if I plan to modi it myself)). Then I choose the various roles that I need in this session and and have a planning phase. After that, the agent is starting implement the changes and I have a manual correction phase.
This flow works for my needs, building idea demos, prototypes or tools for my own sake.
I don't let agent code in our main code base where everything is still hand tailored. That's a conscious decision.
I noticed that the cheaper models (flash, ...) are quite hard to hold back changing files. A question for possible options sometimes results in "yes, I'll go with option A" without asking back.
Frontier models on the other hand love to plan and ask you deliberately for your consent.
I use pi.dev with almost no skills at all to understand how models really work and "feel" to work with.
> A “thinker” who doesn’t write, who skips the step of “merely” synthesizing their vague thoughts into prose, is not thinking. And then these people give their noise to the AI.
OP is quite good with words and has a high standard and world view. The reason why people use AI to manifest their ideas is probably because they have no other way communicate otherwise.
It's a medium to pack the idea into "something" that represents the idea. It was never about a finished and polished product.
It's the sign language for deaf people - a way to show your thoughts.
I'm certain that the people presenting their github repo do put quite some effort (= prompt work) into it, which IS the thinking process.
At the end of the day, most developers are introverts that can think very well but have hard times with soft skills.
Everyone wants to be proud of his work, let us don't blame them how the show it off.
>It's a medium to pack the idea into "something" that represents the idea. It was never about a finished and polished product. It's the sign language for deaf people - a way to show your thoughts.
Sign language is a fully fledged language, as capable of expressing deep and complex thoughts as spoken English. Likening it to some kind of prosthetic for second-rate thinkers is insulting.
The reason why people use AI to manifest their ideas is probably because they have no other way communicate otherwise.
What?! This is nonsense. You’re really making the argument that most people getting LLMs to write for them just couldn’t communicate in any way five years ago?
The five-years-ago internet was certainly full of incoherently expressed ideas (and still is now). For some people AI is just spellcheck on the sentence/paragraph level.
As a reader, I appreciate reading writing that lacks large amounts of spelling mistakes. Everyone agreeing on spelling seems like a useful monoculture, like driving on the same side of the road.
But I don't feel the same way about AI writing. It feels totally different in a way that good spelling does not.
Even if I liked the style, I would object strongly to that style quickly becoming a monoculture.
We're on a path to a style optimized for shallow attention maximization becoming the majority of text we read.
I would love to see the push10k on android playstore/fdroid.
It looks so inviting and motivating that I searched for equivalent alternatives for android but found none!
Would you, maybe, publish it there as well, pleeeease?
The question-tokens define the answer-tokens. That's it. The art relies in clustering the relevant weights together.
reply