HN user
So its basically (a plan + a bunch of file reads + a first edit) injected into the context of a cheap model so the cheap model does not feel like it has to re-read the files and just continues executing and editing?
I think a Q&A-based approach is could also be a suitable way to capture the reasoning behind a project. Instead of writing documentation afterward, an AI could interview the developer throughout the process and preserve the questions and answers as project context.
Matt Pocock’s “grill-me” skill is a nice example of this idea: https://github.com/mattpocock/skills/tree/main/skills/produc...
Did you experiment with the Pruner completely replacing the Reranker?
I'll take it ;)
I started to take VitD on a whim and my mood and energy sure improved. Also I feel like I get sick less often. 3 friends whom I recommended VitD told me the same. Living in northern germany. YMMV.
This mirrors my experience. I have been using it in Pi. It is smart and output is good but it is not efficient in getting there.
Only tangentially related: MiMo-2.5Pro is fast, cheap and very capable, although not quite gpt5.5 level iontelligence (I dont use the claudes). It works flawlessly in Pi and is an excellent workhorse. I expect big things from their next model.
I always feel GPT5.5 is better at ‘getting the bigger picture‘ when I am describing something vaguely vs Chinese models. What’s your experience with that?
What do the model have as inputs? What’s their harness like? Just price data or are they free to pull reports etc. from the web?
Very cool work! Regarding your finding "the tool ran successfully and returned data" and "the tool ran successfully but found nothing." Couldn’t this be solved by designing better tool responses instead of adding another layer in between? Just curious and probing my understanding.
Good old aider ahead of its time
That’s exactly the approach of smolagemts. The only “tool“ available is writing python code
As with so many things aider.chat was ahead of its time with its ability to create deterministic scripts.
Like a special parser? Would you mind elaborating?
How can they fix it after the release? They would have to retrain/finetune it further, no?
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"
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.