Imanari

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"

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

> 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?

absolutely stunning

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

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.

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.

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

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.

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'

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

"I want to implement <XYZ oftentime I use the mic and just ramble[0]>. 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

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.

How does it fare against CC?

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

I like structured outputs as much as the next guy but be careful not to try to structure natural language.

For beginner lifters that might be true initially, but eventually weight will matter.

+1 for good‘ol aider.

It is deliberately NOT a fully agentic tool and this really oftentimes is a benefit. With a little bit of manual work you get exactly the files you want in context and prevent the wrong files from being edited (/read-only). Plus, by skipping on all that agentic thinking and tool calling you save on tokens and edit are faster.

I think a tool call can be thought of as special type of reply where it’s contents are parsed and an actual function is called. A skill is more of a dynamic context-enrichment.

I would like to tell about an unexpected benefit I enjoy as a new farther of a 4 month old. I do mostly 'spec-driven-development' meaning most of the time I am iterating and discussing how things currently work, what are the goals, caveats, edgecases, gotchas etc. Only at the very end actual implementation starts. These spec-documents are on a higher abstraction level than raw code and are far easier to hop on and off and the now frequent interuptions are less detrimental.

Qwens clocks are hilarious

I like it. With this approach it feels like you also don’t need to fiddle as much with the details of your vector search and DB as that portion just gets you going and the actual retrieval happens with grep in a loop.

I get the reasoning behind “letting the agent use grep in a loop“, after all, it is very similar to how humans would explore a document base with ctrl-f. But wouldn’t humans also use vector search all the time if it were as available as ctrl-f? So maybe not ditch vector search but provide it as a tool to the agent. Increased complexity aside, letting the agent explore a huge document base with “vector search in a loop“ should be more powerful that with grep in a loop. Overall I liked the article.

Came here to asks this. This could unlock a super powerful feedback loop towards fantastic health.

So... it should be really good at ARC?

My strategy: actively give yourself permission to just not do the thing, it’s ok! Enjoy your “time off“. This alone sometimes just makes me do the thing eventually kind of out of nowhere.

Could you broadly describe the AI projects you have built?

The following workflow has given me a solid starting point multiple times:

1. > Please ask clarifying questions about {thing you want to implement} and write those into planning.md

2. > Please answer those questions with your best guesses / suggestions.

3. Review and correct the answers from Claude from step 3

3a Repeat 1-3 if needed with follow-up questions.

4. > Go ahead and implement the thing.

In step 3 you can, of course, answer the questions yourself, but letting Claude answer sometimes gives you surprising answers that broaden your vision on the problem a bit.

I am sure you could further automate this with hooks, slash commands, agents, etc., but so far I didn't bother.

Also I have heard great things about Serena-MCP but I haven't tried it myself yet.

> This all started for me about three years ago, when I left a Google review for a doctor saying I felt discriminated against. Shortly after, I got slapped with a legal threat demanding €40,000 in damages. I ended up settling and paying €1,000 in legal fees just to avoid the nightmare of going to court.

They can force you to court over a google review?!

I've been using it within Claude Code via ccr[0] and it feels very similar to Claude 4.

[0] https://github.com/musistudio/claude-code-router