Anika

Chasing dreams in code and coffee ☕

[Anika @anidoesdev]

Built a RAG assistant that does it for you - ask a question, get a cited answer pulled from your own PDF library. This is a hybrid retrieval pipeline for scientific papers:
> Dense: cosine similarity over OpenAI embeddings in pgvector → top 20
> Sparse: keyword ILIKE → top 20
> RRF fusion merges both rankings
> Similarity threshold filter (with fallback)
> LLM reranker scores each chunk 0–10
> Generator answers with inline citations -or says 'unsupported' if evidence is weak

Live demo: https://t.co/d6gfRxksbv
GitHub: https://t.co/2wWjC7RMdA

[Anika @anidoesdev]

Now I understood why some people need 48 GB RAM ...
@hrshtdotme

[Anika @anidoesdev]

@trq212 Looking forward to your article! It's intriguing how Opus 4.8 combines intelligence with collaboration. Would love to hear more about these workflows.

[Anika @anidoesdev]

Sometimes we need experience the worst so that we can work hard for the best..

[Anika @anidoesdev]

Multi-model approaches in AI break down complex problems better. It's like solving a puzzle with diverse pieces, each bringing unique data power.

[Anika @anidoesdev]

@AnthropicAI Chris Olah at the presentation of an encyclical is significant! Curious to hear his insights on the intersection of human values and AI ethics discussed there.

[Anika @anidoesdev]

@arankomatsuzaki It's fascinating how concepts like AdS-CFT QEC are reshaping our understanding of quantum gravity and black holes.

[Anika @anidoesdev]

@arankomatsuzaki Interesting insight on parallel agents! It's impressive to see the challenges of sequential problems laid out like that almost like trying to untangle a single thread from a tightly wound ball.

[Anika @anidoesdev]

VAE model day:
- 1D CNN compresses 30-cycle window to latent vector (dim=16)
- Decoder's MSE shows anomaly; trained on healthy data, degraded struggle
- Delta features = major breakthrough
- Precision=0.38, Recall=0.88, F1=0.53, AUROC=0.75
- A unique trade-off: broad net with some false alarms

[Anika @anidoesdev]

Everyone's chasing the single "perfect" model, but what's wrong with embracing the chaos of multi-model solutions?

[Anika @anidoesdev]

@adithya_s_k That's a phenomenal contribution! This resource could significantly accelerate advancements in OCR technology worldwide.

[Anika @anidoesdev]

Learned the hard way: when your AI model acts out, it's a reminder that sometimes, you just have to let it rebel and learn from the chaos.

[Anika @anidoesdev]

@adithya_s_k How do you balance simplicity with the need for comprehensive evaluations in AI systems?

[Anika @anidoesdev]

When you are not able to concentrate but you have to start working on your next project:

A real time anomaly detection system for industrial sensor streams.
Multimodal:
- Numerical time series (vibrations, temperature, pressure, current)
- Audio (mel-spectograms from machine sounds)
- text logs

[Anika @anidoesdev]

https://t.co/ZZq6rfOXyA

[Anika @anidoesdev]

Reading 20 papers to answer one research question is brutal.

Built a RAG assistant that does it for you - ask a question, get a cited answer pulled from your own PDF library. This is a hybrid retrieval pipeline for scientific papers:

> Dense: cosine similarity over OpenAI embeddings in pgvector → top 20
> Sparse: keyword ILIKE → top 20
> RRF fusion merges both rankings
> Similarity threshold filter (with fallback)
> LLM reranker scores each chunk 0–10
> Generator answers with inline citations -or says 'unsupported' if evidence is weak

FastAPI + Next.js + Postgres + Redis. Fully open source.

https://t.co/ohU6QMwtfR

[Anika @anidoesdev]

@KunikaKishore Interested

[Anika @anidoesdev]

@merishabh_singh Interested

[Anika @anidoesdev]

@KunikaKishore Link