Tim Adelmann

#Digital #Native & #Innovation Enthusiast. #Design Thinker. Software Developer. Keynote Speaker. CTO @ MEETYOO

[Tim Adelmann @tiGGu]

@forefrontvr Nice map! When is it coming?

[Tim Adelmann @tiGGu]

Can an llm in a agentic application decide by itself to summarize the context to safe context?
Can an agent do context engineering on its own?

[Tim Adelmann @tiGGu]

@MikeRyanDev Interesting. I‘ve built my own compiler for streamed Vue components with loading props, slots etc. Text replacements and a bunch of other features.
I see hashbrown is only react/ng?

[Tim Adelmann @tiGGu]

@standupmaths please make an awesome video to explain this!

[Rohan Paul @rohanpaul_ai]

Another AI Math landmark.

GPT 5.2 Pro solved Erdos Problem #397 as well, and it was accepted by Terence Tao.

AI's progress on Math has such huge implecations, as Mathematics is the shared substrate for modeling, and computation across most sciences, so removing mathematical bottlenecks will multiply impact across many fields at once.

So when AI solves core Math problems, everything built on top speeds up.

[Tim Adelmann @tiGGu]

@DennisAdriaans „Back in the day“ destructuring props made them loose reactivity… not sure if this was an exclusive vue 2 thing…

[Robert Scoble @Scobleizer]

Apple should buy Anthropic at any price.

[Tim Adelmann @tiGGu]

@mideysmith POI was ahead of times!

[Tim Adelmann @tiGGu]

I feel like MCP needs some metadata for proper context engineering.
Eg. Context masking (removing tool outputs after some turns to free context) would require some information which tool can be/should be masked.

How should this be done in the current spec?

[Tim Adelmann @tiGGu]

@0xDevShah $20B also seems cheap for Meta or Microsoft don‘t know about anthropic though.

Wondered why nobody is picking this off the market seem to be able to make any llm much faster!

[Tim Adelmann @tiGGu]

@yutozxx Menopause

[Tim Adelmann @tiGGu]

@YBenlemlih @typescript @mattpocockuk For me having both interfaces and types which are basically the same, is a major design flaw of typescript.
In other languages interfaces have a clear role: they define behavior and always end with -able like „serializable“.

I personally always use types. Never interfaces

[Tim Adelmann @tiGGu]

@tekbog Jakob‘s law: „Users spend most of their time on other sites. This means that users prefer your site to work the same way as all the other sites they already know.“ https://t.co/YgWwA5kyaf

[Tim Adelmann @tiGGu]

@SepzenoOfficial The expanse

[Tim Adelmann @tiGGu]

My year in code. @cursor_ai
There are a couple of days left in 2025. I‘m confident i will reach the 1T until the end of 2025!

The most amazing thing this year was the rate of improvements of models and IDE!

Thank you

[Tim Adelmann @tiGGu]

Hot take: The only good reason to use an SLM is if you're running on-device.

For cloud/enterprise, the future isn't "Small Models." It's Smart Routing. The true achievement of GPT-5

Don't optimize by shrinking your intelligence. Optimize by routing your traffic.

[Tim Adelmann @tiGGu]

Two massive deals: OpenAI's $1B Disney IP grab for Sora + Netflix's Warner Bros bid.

Why? AI video abundance is here. Attention is scarce—IP is the ultimate moat for beloved slop (Star Wars floods incoming).

Netflix fights TikTok/IG too, not just Prime.

[Tim Adelmann @tiGGu]

I always thought putting 2 of the same icons next to each other is bad UX.
Well I‘m definetly confused. Always press the wrong (X) … liquid (gl)ass

[Tim Adelmann @tiGGu]

AI agents need data, but you can't let them run wild in your production database.

Our solution: A secure, in-flight sandbox. The agent can now explore, analyze, and visualize customer data autonomously and safely.

[Tim Adelmann @tiGGu]

Css anchor is around the corner.
Finally one of the most anticipated APIs in the web.

I guess @jaffathecake is to he thanked for the FF support.

[Tim Adelmann @tiGGu]

The lesson: The smartest AI isn't a single genius, it's a committee of experts. This has huge implications for building AI products.

read the analysis:
https://t.co/jwkIltT38o

[Tim Adelmann @tiGGu]

The biggest myth in AI right now? That one "super model" has all the answers.

We tested 17 LLMs on a video analysis task. They didn't agree. Instead, they formed "opinion clusters," each finding different highlights.