HackerTrans
TopNewTrendsCommentsPastAskShowJobs

enricoros

no profile record

Submissions

Kimi K2.5 is significantly less censored than K2

big-agi.com
4 points·by enricoros·6 ay önce·1 comments

Show HN: Big-AGI 2 – Spent a year obsessing over AI for thinking

github.com
3 points·by enricoros·9 ay önce·1 comments

Show HN: Beam – Find Better Answers with Multi-Model AI Reasoning

big-agi.com
18 points·by enricoros·2 yıl önce·16 comments

Show HN: Next.js ChatGPT – Responsive chat application powered by GPT-4

github.com
126 points·by enricoros·3 yıl önce·34 comments

comments

enricoros
·6 ay önce·discuss
CCP-bench has gotten WAY better on K2.5!

https://big-agi.com/static/kimi-k2.5-less-censored.jpg
enricoros
·6 ay önce·discuss
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.
enricoros
·2 yıl önce·discuss
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 :)
enricoros
·2 yıl önce·discuss
Thank you so much - there's much more and much better coming ;)
enricoros
·2 yıl önce·discuss
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.
enricoros
·2 yıl önce·discuss
Same experience. Once you beam you look for it everywhere!
enricoros
·2 yıl önce·discuss
Same. I like using Opus | Gpt-4 | Gemini Pro (I don't have Ultra) | Mistral Large.
enricoros
·2 yıl önce·discuss
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.
enricoros
·3 yıl önce·discuss
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 Documentation: lacking, inadequate, outdated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
enricoros
·3 yıl önce·discuss
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.
enricoros
·3 yıl önce·discuss
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.
enricoros
·3 yıl önce·discuss
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' :)
enricoros
·3 yıl önce·discuss
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!
enricoros
·3 yıl önce·discuss
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.
enricoros
·3 yıl önce·discuss
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