Hacker News: Imanari

New comment by Imanari in "Show HN: Semble – Code search for agents that uses 98% fewer tokens than grep"

Imanari — Mon, 18 May 2026 07:25:13 +0000

Good old aider ahead of its time

New comment by Imanari in "Agents need control flow, not more prompts"

Imanari — Fri, 08 May 2026 10:57:44 +0000

That’s exactly the approach of smolagemts. The only “tool“ available is writing python code

New comment by Imanari in "Agents need control flow, not more prompts"

Imanari — Fri, 08 May 2026 10:20:33 +0000

As with so many things aider.chat was ahead of its time with its ability to create deterministic scripts.

New comment by Imanari in "DeepSeek v4"

Imanari — Fri, 24 Apr 2026 19:19:09 +0000

Like a special parser? Would you mind elaborating?

New comment by Imanari in "DeepSeek v4"

Imanari — Fri, 24 Apr 2026 06:19:58 +0000

How can they fix it after the release? They would have to retrain/finetune it further, no?

New comment by Imanari in "DeepSeek v4"

Imanari — Fri, 24 Apr 2026 06:02:43 +0000

Just tested it via openrounter in the Pi Coding agent and it regularly fails to use the read and write tool correctly, very disappointing. Anyone know a fix besides prompting "always use the provided tools instead of writing your own call"

New comment by Imanari in "MiMo-v2.5-Pro"

Imanari — Thu, 23 Apr 2026 06:42:43 +0000

Why do the Xiami releases never get any attention? Mimo-V2-Pro was pretty good, excited to try V2.5

New comment by Imanari in "Stop trying to engineer your way out of listening to people"

Imanari — Mon, 20 Apr 2026 10:39:05 +0000

> Listening often means not jumping to a solution; but absorbing and processing someone’s pain

> When in actuality, they should [...] finding a way to solve the pain points

Honest question, how do I 'absorb someones pain'? And how do I transition from that into eventually formulating the feature/ticket?

New comment by Imanari in "God Sleeps in the Minerals"

Imanari — Wed, 15 Apr 2026 17:39:05 +0000

absolutely stunning

New comment by Imanari in "Running Gemma 4 locally with LM Studio's new headless CLI and Claude Code"

Imanari — Mon, 06 Apr 2026 14:18:31 +0000

How well do the Gemma 4 models perform on agentic coding? What are your impressions?

New comment by Imanari in "Components of a Coding Agent"

Imanari — Sun, 05 Apr 2026 07:15:39 +0000

I will also leave this here

https://github.com/shareAI-lab/learn-claude-code/tree/main/a...

I found it excellent in explaining a CC-like coding agent in layers.

New comment by Imanari in "LLM Wiki – example of an "idea file""

Imanari — Sun, 05 Apr 2026 06:56:17 +0000

Isn’t this just kicking the can down the road?

> but the LLM is rediscovering knowledge from scratch on every question

Unless the wiki stays fully in context now the LLM hast to re-read the wiki instead of re-reading the source files. Also this will introduce and accumulate subtle errors as we start to regurgitate 2nd-order information.

I totally get the idea but I think next gen models with 10M context and/or 1000tps will make this obsolete.

New comment by Imanari in "Further human + AI + proof assistant work on Knuth's "Claude Cycles" problem"

Imanari — Sun, 29 Mar 2026 09:06:56 +0000

Maybe to be better able to restart the process and not lose track.

New comment by Imanari in "Show HN: Duplicate 3 layers in a 24B LLM, logical deduction .22→.76. No training"

Imanari — Thu, 19 Mar 2026 09:37:23 +0000

Fascinating! I wonder if new training techniques could emerge from this. If we say layer-1=translater, layer2-5=reasoner, layer6 retranslater, could we train small 6 layer models but evaluate their performance in a 1>n*(2-5)>6 setup to directly train towards optimal middle-layers that can be looped? You'd only have to train 6 layers but get the duplication-benefit of the middle layers for free.

New comment by Imanari in "We don't need continual learning for AGI. What top labs are currently doing"

Imanari — Thu, 05 Mar 2026 14:47:47 +0000

I don't know who you are and how you are so sure about 'what top labs are actually doing' but I have a similar feeling about the issue. The models dont have to 'actually learn', the setup has to approximate 'actual learning' just well enough to be usefull.

> AND it can inherit all the accumulated memories/docs from its predecessor.

So we are talking about a whole system, not just the model? Reminds me of something I heard a while back 'AGI will be a product, not a model'

New comment by Imanari in "How will OpenAI compete?"

Imanari — Thu, 26 Feb 2026 20:06:20 +0000

How is gemini 3.1 doing in agentic harnesses? Did they catch up?

New comment by Imanari in "Ask HN: Are you still using spec driven development?"

Imanari — Thu, 05 Feb 2026 08:25:26 +0000

"I want to implement . Please explore the codebase and figure out how things work. Write down any questions you have. Then write an implementation plan. Do all of this in a dedicated markdown file."

The questions are usually 80% useless but those 20% often do point me to stuff I have not considered.

Then I edit the markdown manually or discuss some parts with the agent.

"go ahead and implement"

[0] - https://github.com/cjpais/Handy

New comment by Imanari in "Kimi K2.5 Technical Report [pdf]"

Imanari — Fri, 30 Jan 2026 23:26:34 +0000

I have been very impressed with this model and also with the Kimi CLI. I have been using it with the 'Moderato' plan (7 days free, then 19$). A true competitor to Claude Code with Opus.

New comment by Imanari in "Kimi Released Kimi K2.5, Open-Source Visual SOTA-Agentic Model"

Imanari — Tue, 27 Jan 2026 13:17:01 +0000

How does it fare against CC?

New comment by Imanari in "Show HN: I quit coding years ago. AI brought me back"

Imanari — Tue, 20 Jan 2026 08:47:58 +0000

Very nice retirement calculater - clean, intuitive and rich in settings.