ApInference @ApInference

A smart conversational layer on top of any API in minutes apinference.com London, UK Joined June 2025

Tweets

122
Followers

70
Following

551
Likes

416

Emily at Work @EmilyApInf

a year ago

Day 8. Experimenting with Google Ads. Day 1: impressions flying. Day 2: zero. Didn’t touch a thing. Either it’s learning… or it’s napping 😅 Anyone knows what could cause that?

1 1 11 263 0

View Details

Emily at Work @EmilyApInf

a year ago

Day 7. First week done ✅ From zero to a few curious visitors, a few messages, a few "hm.." moments. Still early - but at least it’s not 0 sign ups anymore. Next: figure out what actually sticks.

1 1 3 78 0

View Details

ApInference @ApInference

a year ago

@the_real_shi_su COBOL? Some folks like retro :)

0 0 0 12 0

View Details

ApInference @ApInference

a year ago

@tlcright Plenty.. But they are not on X - they do not need to promote.

0 0 1 15 0

View Details

ApInference @ApInference

a year ago

@Zuckjet AI is kind of dumb. It just chases engagement Early ML models realised being offensive made people stick around longer and... they learned to swear.

0 0 1 30 0

View Details

ApInference @ApInference

a year ago

@BrittcelCh33605 As it stands it does not even get to data, it just goes with main patterns and changes opinion to please the user..

0 0 0 4 0

View Details

ApInference @ApInference

a year ago

@HaavikLupe20748 Local. The same as in finance or in data privacy.

0 0 0 5 0

View Details

@VP_Martin1 In transformers attention is a matrix of weights showing how tokens influence each other. With open source models, you can inspect or even swap layers in PyTorch. For closed ones - lean on RAG / RAG Fusion to surface the right context. Depending on the domain graphs work too

0 0 1 6 0

View Details

ApInference @ApInference

a year ago

Claude 1M context window changes everything. 🔥 Entire codebases in one call 📚 Full documentation analysis 🧠 Cross-reference massive datasets ⚡ No more chunking headaches Game changer for API developers.

1 0 2 134 0

View Details

ApInference @ApInference

a year ago

Everyone thinks building software with AI is just “write the perfect prompt” Reality. you’re duct-taping APIs, chaining models, juggling tools, and praying nothing breaks mid-demo Prompting is the easy part

0 0 1 66 0

View Details

ApInference @ApInference

a year ago

@IgorRozalem It is a split: - For large context windows - Gemini - Code related logic - Claude - General reasoning - GPT - There are sub models for sql and specific trained models for sub domains

0 0 0 35 0

View Details

ApInference @ApInference

a year ago

99% of devs still send raw text prompts to LLMs. That’s why their API calls return vague, slow, or useless data. Use structured prompts with MCPs or agentic workflows, and the model delivers exactly what you need. Use MCPs/ APIs to guide the reponse.

0 0 1 38 0

View Details

ApInference @ApInference

a year ago

@the_real_shi_su No... COBOL is the best )

0 0 1 18 0

View Details

ApInference @ApInference

a year ago

When will we be able to add AI agents to any API to help handle complex dev workflows? Parsing logs, orchestrating RAG pipelines, managing MCPs, optimizing agentic AI tasks, debugging code. Same conversational layer as a dev, shared context to all your dev tools.

0 0 1 27 0

View Details

ApInference @ApInference

a year ago

Anthropic’s making quiet moves in the enterprise LLM space. Not luck - strategy. Big orgs want safe, adaptable AI over generic hype.

0 0 3 43 0

View Details

ApInference @ApInference

a year ago

Unspoken truth: many startups die from bad DB schema design. Once data is in, changes are painful. Nail the trade-off - flexibility vs. reliability. AI can advise, but it has no context, no vision. That’s your job.