enricoros
Re:Kimi Released Kimi K2.5, Open-Source Visual SOTA-Agentic Model
on Tuesday January 27, 2026 @05:01PM (#46787609)
CCP-bench has gotten WAY better on K2.5!
Re:Kimi K2.5 is significantly less censored than K2
on Tuesday January 27, 2026 @03:33PM (#46786159)
Same ask, same session, side by side, no system prompt. K2 Preview refuses, K2.5 gives factual history.
Frankly surprising and welcome to see loosening CCP-sensitive topics between model versions.
Show HN: Big-AGI 2 – Spent a year obsessing over AI for thinking
https://github.com/enricoros/big-AGI/releases/tag/v2.0.0
Hey HN, Enrico here. Some of you might remember Big-AGI from early chat days. The response here pushed me to quit my job and go all-in. Spent the last year rebuilding it properly (mostly hand-written) instead of shipping fast.This is the tool I couldn't find: the AI you use to decide what to build, and why, before going to Claude Code or Cursor.Even though the hype is on AI that 'does' things...
Re:Show HN: Beam – Find Better Answers with Multi-Model AI Reasoning
on Monday April 01, 2024 @11:21PM (#39902062)
One person on Discord has called this 'taking the idea of self-consistency forward to ensemble model usage'. I guess this is, technically, what this approach is about :)
Re:Show HN: Beam – Find Better Answers with Multi-Model AI Reasoning
on Monday April 01, 2024 @11:15PM (#39902035)
Thank you so much - there's much more and much better coming ;)
Re:Show HN: Beam – Find Better Answers with Multi-Model AI Reasoning
on Monday April 01, 2024 @08:10PM (#39900951)
Yes, the only issue is the usage of tokens, which is obviously greater as we are sampling more of the solutions space. But it's a compromise to have GPT-4.5 level intelligence with GPT-4.
Re:Show HN: Beam – Find Better Answers with Multi-Model AI Reasoning
on Monday April 01, 2024 @07:10PM (#39900473)
Same experience. Once you beam you look for it everywhere!
Re:Show HN: Beam – Find Better Answers with Multi-Model AI Reasoning
on Monday April 01, 2024 @07:09PM (#39900470)
Same. I like using Opus | Gpt-4 | Gemini Pro (I don't have Ultra) | Mistral Large.
Re:Show HN: Beam – Find Better Answers with Multi-Model AI Reasoning
on Monday April 01, 2024 @07:08PM (#39900464)
There's a combo box on the right side, and when you click on the "Add Merge" (green) button, the currently active model will be selected.
Show HN: Beam – Find Better Answers with Multi-Model AI Reasoning
https://big-agi.com/blog/beam-multi-model-ai-reasoning
HN, first things first: one year ago you make me believe in my opensource AI project, and I'm forever grateful[1].I am back with Beam - a technique to use diverse LLMs to generate responses, and Merge them - all within a snappy UX. I am no researcher, so you'll find a dark-mode blog, and not a light-mode PDF on arxiv :) Blog, open code, and live hosted demo, all published.You can use Beam early...
Re:LangChain Announces 10M Seed Round
on Tuesday April 04, 2023 @04:53PM (#35445732)
TL;DR & DIY: asked gpt-4 this prompt "Cluster the top10 categories of complaints by the users, and describe each category with a few adjectives/nouns in order or importance." as of rn.
Crisp or too critical?
1. Documentation: lacking, inadequate, outdated
2. Code quality: simple, awkward, suboptimal
3. Production readiness: experimental, unreliable, limited
4. Monetization: unclear, risky, potentially detrimental to open-source
5. Community support: misinformation, poor communication, fragmented
6. Ecosystem: competing alternatives, redundancy, unclear positioning
7. Business model: potential rug-pull, VC-funded, uncertain sustainability
8. Developer experience: poor ergonomics, type erasure, confusing
9. Performance: slow, afterthought, poor observability
10. Maintenance: unpatched bugs, slow response to issues, dependency on contributors
Re:Show HN: LiveQuery GPT-4 – Chatbot with Real-Time Search
on Friday March 24, 2023 @04:46AM (#35286589)
Very interesting to follow the chain on the console. Vry good in breaking down multi-part questions, way better than Google Assistant - and then uses G to search. Thx for showing the way.
Re:Make your own ChatGPT UI
on Monday March 20, 2023 @05:56AM (#35229344)
Very good point. Once you start breaking down a llm into presets/delegators, you introduce basically if-else, with all the problems of that split. Lack of visibility, local vs global optimization, lack of control and predictability, asymmetry of information. I wonder if the current Agents approach is a stopgap solution.
Re:Make your own ChatGPT UI
on Monday March 20, 2023 @05:47AM (#35229277)
When the user selects one of those, any query will reveal the prompt. Can be changed but the change won't be persisted yet. We added a 'Custom' preset today that requires editing. Agree with your point tho - rn editing happens via 'forking' :)
Re:Make your own ChatGPT UI
on Monday March 20, 2023 @05:45AM (#35229259)
OP: I went to sleep with this as my 1st post and 1 star, and woke up with a PR for 3.5-Turbo pending. Community for the win!
Re:Make your own ChatGPT UI
on Monday March 20, 2023 @05:44AM (#35229253)
Hey guys, op here. Merged the PR for 3.5-Turbo support and cleaned up the code (very good observations on all the places 'gpt-4' was hardcoded). Combo box to select the model. GPT-4 will need a 4-enabled key, while 3.5-Turbo will work with any GPT key.
Re:Make your own ChatGPT UI
on Sunday March 19, 2023 @06:02AM (#35217537)
What does it take to make a basic ChatGPT-like frontend, with code highlighting, run in sandbox, drop-files, and 'acting' in prompts? Clone away and enjoy. First time poster