Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

You should write an agent

fly.io

Post reply on HN
Print view View original

211–220 of 409 posts

Re: You should write an agent

#211

Post by nostrebored »

andai wrote: post #197
ericd wrote: post #41

Absolutely, especially the part about just rolling your own alternative to Claude Code - build your own lightsaber. Having your coding agent improve itself is a pretty magical experience. And then you can trivially swap in whatever model you want (Cerebras is crazy fast, for example, which makes a big difference for these many-turn tool call conversations with big lumps of context, though gpt-oss 120b is obviously no…

What are you using for transcription? I tried Whisper, but it's slow and not great. I tried the gpt audio models, but they're trained to refuse to transcribe things. I tried Google's models and they were terrible. I ended up using one of Mistral's models, which is alright and very fast except sometimes it will respond to the text instead of transcribing it. So I'll occasionally end up with pages of LLM rambling paste…

Parakeet is sota

Re: You should write an agent

#212

Post by dSebastien »

nostrebored wrote: post #211
andai wrote: post #197

Earlier quoted context omitted.

What are you using for transcription? I tried Whisper, but it's slow and not great. I tried the gpt audio models, but they're trained to refuse to transcribe things. I tried Google's models and they were terrible. I ended up using one of Mistral's models, which is alright and very fast except sometimes it will respond to the text instead of transcribing it. So I'll occasionally end up with pages of LLM rambling paste…

Parakeet is sota

Agreed. I just launched https://voice-ai.knowii.net and am really a fan of Parakeet now. What it manages to achieve locally without hogging too much resources is awesome

Re: You should write an agent

#213

Post by ericd »

andai wrote: post #197
ericd wrote: post #41

Absolutely, especially the part about just rolling your own alternative to Claude Code - build your own lightsaber. Having your coding agent improve itself is a pretty magical experience. And then you can trivially swap in whatever model you want (Cerebras is crazy fast, for example, which makes a big difference for these many-turn tool call conversations with big lumps of context, though gpt-oss 120b is obviously no…

What are you using for transcription? I tried Whisper, but it's slow and not great. I tried the gpt audio models, but they're trained to refuse to transcribe things. I tried Google's models and they were terrible. I ended up using one of Mistral's models, which is alright and very fast except sometimes it will respond to the text instead of transcribing it. So I'll occasionally end up with pages of LLM rambling paste…

Whisper.cpp/Faster-whisper are a good bit faster than OpenAI's implementation. I've found the larger whisper models to be surprisingly good in terms of transcription quality, even with our young children, but I'm sure it varies depending on the speaker, no idea how well it handles heavy accents.

I'm mostly running this on an M4 Max, so pretty good, but not an exotic GPU or anything. But with that setup, multiple sentences usually transcribe quickly enough that it doesn't really feel like much of a delay.

If you want something polished for system-wide use rather than rolling your own, I've been liking MacWhisper on the Mac side, currently hunting for something on Arch.

Re: You should write an agent

#214

Post by aaronblohowiak »

THEY SEND THE WHOLE CONTEXT EVERY TIME? Man that seems... not great. sometimes it will go off and spin on something.. seems like it would be a LOT better to roll back than to send a corrective message. hmmm...... this article is nerd-sniping on a massive scale ;D

Re: You should write an agent

#215

Post by keyle »

dave1010uk wrote: post #80

Two years ago I wrote an agent in 25 lines of PHP [0]. It was surprisingly effective, even back then before tool calling was a thing and you had to coax the LLM into returning structured output. I think it even worked with GPT-3.5 for trivial things. In my mind LLMs are just UNIX strong manipulation tools like `sed` or `awk`: you give them an input and command and they give you an output. This is especially true if y…

> a small Autobot that you can't trust

That gave me a hearty chuckle!

Re: You should write an agent

#216

Post by whatevertrevor »

khimaros wrote: post #178
ilikehurdles wrote: post #127

Earlier quoted context omitted.

I don't think hn is reflective of where programmers are today, culturally. 10 years ago, sure, it probably was.

what place is more reflective today?

I don't know about online forums, but all my IRL friends have a lot more balanced takes on AI than this forum. And honestly it extends beyond this forum to the wider internet. Online, the discourse seems extremely polarized: either it's all a pyramid scheme or stories about how development jobs are already defunct and AI can supervise AI etc.

Re: You should write an agent

#217

Post by tptacek »

aaronblohowiak wrote: post #214

THEY SEND THE WHOLE CONTEXT EVERY TIME? Man that seems... not great. sometimes it will go off and spin on something.. seems like it would be a LOT better to roll back than to send a corrective message. hmmm...... this article is nerd-sniping on a massive scale ;D

In the Responses API, you can implicitly chain messages with `previous_response_id` (I'm not sure how old a conversation you can resurrect that way). But I think Codex CLI actually sends the full context every time? And keep in mind, sending the whole context gives you fine-grained control over what does and doesn't appear in your context window.

Anyways, if it nerd sniped you, I succeeded. :)

Re: You should write an agent

#218

Post by Uehreka »

ericd wrote: post #41

Absolutely, especially the part about just rolling your own alternative to Claude Code - build your own lightsaber. Having your coding agent improve itself is a pretty magical experience. And then you can trivially swap in whatever model you want (Cerebras is crazy fast, for example, which makes a big difference for these many-turn tool call conversations with big lumps of context, though gpt-oss 120b is obviously no…

The reason a lot of people don’t do this is because Claude Code lets you use a Claude Max subscription to get virtually unlimited tokens. If you’re using this stuff for your job, Claude Max ends up being like 10x the value of paying by the token, it’s basically mandatory. And you can’t use your Claude Max subscription for tools other than Claude Code (for TOS reasons. And they’ll likely catch you eventually if you try to extract and reuse access tokens).

Re: You should write an agent

#219

Post by larusso »

Just the other day we tried to explain inner workings of cursor etc to a bunch of colleagues who had a very complicated view how these agents achieve what they do. Awesome post. Makes it easier for me the next time. The options are so big. But one should say that an agent with file access etc, is easy to write but hard to control. If you want to build yourself a general coding agent a bit more thought needs to be put into the whole thing. Otherwise you might end up with a “dd -if=/dev/random -of=/“ or something ^^ and happily execute it.

Re: You should write an agent

#220

Post by simonw »

AdieuToLogic wrote: post #188
mrkurt wrote: post #75

Earlier quoted context omitted.

Claude Code is an obfuscated javascript app. You can point Claude Code at it's own package and it will pretty reliably tell you how it works. I think Claude Code's magic is that Anthropic is happy to burn tokens. The loop itself is not all that interesting. What is interesting is how they manage the context window over a long chat. And I think a fair amount of that is serverside.

> Claude Code is an obfuscated javascript app. You can point Claude Code at it's own package and it will pretty reliably tell you how it works. This is why I keep coming back to Hacker News. If the above is not a quintessential "hack", then I've never seen one. Bravo!

I've been running the obfuscated code through Prettier first, which I think makes it a bit easier for Claude Code to run grep against.
Post reply on HN