Hacker News: bestcoder69

Technical Details of My LLM-Generated Book

bestcoder69 — Tue, 10 Feb 2026 18:06:32 +0000

Article URL: https://mattbruenig.com/2026/02/10/technical-details-of-my-llm-generated-book/

Comments URL: https://news.ycombinator.com/item?id=46964107

Points: 3

# Comments: 0

New comment by bestcoder69 in "Llama.cpp supports Vulkan. why doesn't Ollama?"

bestcoder69 — Fri, 31 Jan 2025 13:57:54 +0000

Llamafile: https://github.com/Mozilla-Ocho/llamafile

New comment by bestcoder69 in "Amazon Makes It Harder for Disabled Employees to Work from Home"

bestcoder69 — Thu, 14 Nov 2024 01:31:45 +0000

permitted to force RTO without any data != ought to force RTO without any data

New comment by bestcoder69 in "Why we no longer use LangChain for building our AI agents"

bestcoder69 — Fri, 21 Jun 2024 16:46:17 +0000

I can already use multiple backends by writing different code. The value-add langchain would need to prove is whether i can get better results using their abstractions compared to me doing it manually. Every time I’ve looked at how langchain’s prompts are constructed, they went wayyy against LLM vendor guidance so I have doubts.

Also the downside of not being able to easily tweak prompts based on experiments (crucial!)

And not to mention the library doesn’t actually live up to this use case, and you immediately (IME) run into “you actually can’t use a _Chain with provider _ if you want to use their _ API”, so I ultimately did have to care about whats supposed to be abstracted over

New comment by bestcoder69 in "Why we no longer use LangChain for building our AI agents"

bestcoder69 — Fri, 21 Jun 2024 16:39:30 +0000

They’ve been growth hacking the whole time pretty much, optimizing for virality. Eg integrating with every ai thing under the sun, so they could publish a seo-friendly “use gpt3 with someVecDb and lang chain” page, but for every permutation you can think. Easy for them to write since langchains abstractions are just unnecessary wrappers. They’ve also had meetups since very early on. The design seems to make langchain hard to remove since you’re no longer doing functional composition like you’d do in normal python - you’re combining Chains. You can’t insert your own log statements in between their calls so you have to onboard to langsmith for observability (their saas play). Now they have a DSL with their own binary operators :[

VC-backed, if you couldn’t guess already

New comment by bestcoder69 in "Why we no longer use LangChain for building our AI agents"

bestcoder69 — Fri, 21 Jun 2024 16:32:52 +0000

openai cookbook! Instructor is a decent library that can help with the annoying parts without abstracting the whole api call - see it’s docs for RAG examples.

New comment by bestcoder69 in "Why we no longer use LangChain for building our AI agents"

bestcoder69 — Fri, 21 Jun 2024 10:57:17 +0000

They released chat and non-chat (completion) versions of 3.5 at the same time so not really; the switch to chat model was orthogonal.

e: actually some of the pre-chatgpt models like code-davinci may have been considered part of the 3.5 series too

New comment by bestcoder69 in "Tyler Perry Puts $800M Studio Expansion on Hold After Seeing OpenAI's Sora"

bestcoder69 — Fri, 23 Feb 2024 02:09:42 +0000

limewire teens were pioneers too

New comment by bestcoder69 in ".ai website registrations are a windfall for tiny Anguilla"

bestcoder69 — Wed, 31 Jan 2024 05:36:00 +0000

together.xyz, although they’re .ai now

New comment by bestcoder69 in "Should children clean their own schools? Japan thinks so"

bestcoder69 — Mon, 04 Dec 2023 03:33:44 +0000

Newt Gingrich proposed once that we make kids do this, but it was just gonna be for the poor kids.

New comment by bestcoder69 in "Tesla faces strong oposition from unions in Sweden"

bestcoder69 — Fri, 17 Nov 2023 14:49:50 +0000

Tesla could just negotiate instead of being antagonistic.

New comment by bestcoder69 in "Sam Bankman-Fried Convicted"

bestcoder69 — Fri, 03 Nov 2023 04:14:25 +0000

Prosecutors need snitches.

New comment by bestcoder69 in "Powering AI could use as much electricity as a small country"

bestcoder69 — Wed, 11 Oct 2023 01:32:27 +0000

> This extreme scenario is unlikely to happen in the short term because of the high costs associated with additional AI servers and bottlenecks in the AI server supply chain, de Vries says.

If we suddenly start ignoring the costs, it could get very expensive, indeed.

New comment by bestcoder69 in "Ask HN: How do you use AI to get things done faster?"

bestcoder69 — Thu, 28 Sep 2023 11:57:04 +0000

Prompts:

- does this API design make sense?

- my team thinks __ is a good pattern, what are some cons?

- what’s a good name for a class that does x,y,z

- is this code snippet readable?

- write a bash script to automate this very tiny thing

- upload quickjs binary to the advanced data analysis model and ask it to micro benchmark a couple of approaches to the same thing

New comment by bestcoder69 in "Ask HN: Would criminalizing long commutes improve quality of life?"

bestcoder69 — Sun, 24 Sep 2023 20:26:32 +0000

A cleaner policy would be to ban cars. Probably need a transition in between, but that's definitely the destination. In the year 3000 our asses better not be sitting in traffic in single-passenger vehicles w/ 3 seats empty still for some reason.

New comment by bestcoder69 in "Ask HN: Would criminalizing long commutes improve quality of life?"

bestcoder69 — Sun, 24 Sep 2023 20:24:16 +0000

Maybe workers will strike for... more detailed information about each worker's individual profit margin?

New comment by bestcoder69 in "Ask HN: Would criminalizing long commutes improve quality of life?"

bestcoder69 — Sun, 24 Sep 2023 20:23:31 +0000

And if I could breath underwater I wouldn't need a scuba tank.

New comment by bestcoder69 in "A literary history of fake texts in Apple's marketing materials"

bestcoder69 — Sun, 17 Sep 2023 17:51:33 +0000

He's analyzing what looks good in marketing copy.

New comment by bestcoder69 in "Efficient Memory Management for Large Language Model Serving with PagedAttention"

bestcoder69 — Thu, 14 Sep 2023 19:25:37 +0000

Maybe if you have a model with a large context window, you stuff a document in the prompt as a prefix, then ask a bunch of different questions about the document?

New comment by bestcoder69 in "Tesla FSD Beta tried to kill me last night"

bestcoder69 — Sun, 03 Sep 2023 20:19:20 +0000

Self-driving cars work really well so far. But we'll see, I guess! https://arstechnica.com/cars/2023/09/are-self-driving-cars-a...