Very impressed with this lil guy and it deserves more downloads. It's based on the original version of Qwen3-4B but find that it questions reality way less often. Jan-v1 seems to think that everything it sees is synthetic data and constantly gaslights me
It's just a matter of time before all the data leakage and data scraping associated with building, training, and using AI results in some kind of major scandal.
longer context doesn't generate better responses. it can even hurt your llm/agent. 1M context window doesn't automatically make models smarter as it's not about the size; it's how you use it.
here are 4 types of context failure and why each one happens:
1. context poisoning: if hallucination finds its way into your context, the agent will rely on that false information to make its future moves. for example if the agent hallucinates about the "task description", all of its planning to solve the task would also be corrupt.
2. context distraction: when the context becomes too bloated, the model focuses too much on it rather than come up with novel ideas or to follow what it has learned during training. as Gemini 2.5 Pro technical report points out, as context grows significantly from 100K tokens, "the agent showed a tendency toward favoring repeating actions from its vast history rather than synthesizing novel plans".
3. context confusion: everyone lost it when MCPs became popular, it seemed like AGI was achieved. I suspected there is something wrong and there was: it's not just about providing tools, bloating the context with tool use derails the model from selecting the right one! even if you can fit all your tool metadata in the context, as their number grows, the model gets confused over which one to pick.
4. Context Clash: if you exchange conversation with a model step by step and provide information as you go along, chances are you get worse performance rather than providing all the useful information at once. one the model's context fills with wrong information, it's more difficult to guide it to embrace the right info. agents pull information from tools, documents, user queries, etc. and there is a chance that some of these information contradict each other, and it's not good new for agentic applications.
Qwen 3 Coder is a personal attack to k2, and I love it. It achieves near SOTA on LCB while not having reasoning. Finally people are understanding that reasoning isnt necessary for high benches...
just submitted my plugin idea to the G-Assist Plugin Hackathon by @nvidia . Check it out, it's a great way to use a local SLA model on a windows machine to easily and locally get things done ! https://github.com/NVIDIA/G-Assist
Anyone know how to reset Claude web's MCP config? I connected mine when the HF MCP first released with just the default example spaces added. I added lots of other MCP spaces but Claude.ai doesn't update the available tools... "Disconnecting" the HF integration does nothing, deleting it and adding it again does nothing.
Refreshing tools works fine in VS Code because I can manually restart it in mcp.json, but claude.ai has no such option. Anyone got any ideas?
So every bio/med/chem meeting i go to i always the same questions "why are you sharing a gdrive link with me for this?" and "Do you have any plans to publish your model weights and datasets on huggingface?" and finally i got a good answer today which explains everything :
basically there is some kind of government censorship on this (usa, but i'm sure others too) and they are told they are not allowed as it is considered a "dataleak" which is illegal !!!!
this is terrible ! but the good news is that we can do something about it !
60+ Generative AI projects for your resume. grind this GitHub repo if you want to level up: > LLM fine-tuning and applications > advanced RAG apps > Agentic AI projects > MCP and A2A (new)
this book actually exists for free, βthe little book of deep learningβ. best to refresh your mind about DL basics: > foundations of machine learning > how models train > common layers (dropout, poolingβ¦) > basic intro to LLMs actually optimized for mobile.
