Ygor Lemos

CTO @ || ex-CTO & Co-Founder @ @pinion 🦄📲 - Software Engineer / Architect ↔️ C, Python, Swift, Go, Linux, MongoDB, k8s, AI __ opinions are my own.

[Ygor Lemos @ygbr]

“Models are Opinions Embedded in Mathematics”
— Cathy O’Neil In Weapons of Math Destruction

[Kavsoft @_Kavsoft]

Starting with iOS 27, we can actually convert a tab bar to a sidebar.
A new modifier was introduced to do this.
“.defaultTabBarPlacement(.sidebar)”

As of current testing, this seems to work on iPhones as well when the app is in landscape mode. This is the same behavior used in the iPhone Health app, where the tab bar converts into a sidebar in landscape mode!

[Harrison Kinsley @Sentdex]

While closed source AI is in shambles, open source is having one of the best weeks of all time.

Z ai GLM 5.2
Minimax M3
Kimi 2.7 code

[starmex @starmexxx]

AMD CEO LISA SU HELD A MINI PC ON STAGE THAT RUNS A 235B MODEL AND REPLACES YOUR $440/MONTH AI STACK

amd's ryzen ai max+ 395 is the first x86 chip that runs a 200 billion parameter model on one piece of silicon. cpu and gpu share 128gb of unified memory, no separate graphics card needed

the gmktec evo-x2 runs qwen3 235b fully, deepseek v3 comfortably and llama 3.3 70b with headroom. on linux you get 110gb of usable vram out of 128gb

amd claimed the chip beat an nvidia rtx 5080 by more than 3x on deepseek r1 inference. a lunchbox sized pc outrunning a $1,000 discrete gpu on a real ai workload

a heavy ai user pays $200 for claude code max, $200 for chatgpt pro, $20 for cursor and $20 for gemini. that's $5,280 a year and the box pays itself off in 9 to 10 months

install ollama, pull the model, point claude code at localhost. same interface, nothing leaves the machine, nothing costs per request

bookmark this and read the article below

[Justin Schroeder @jpschroeder]

Fable isn't the first.

In 1999 the department of defense blocked exports of the PowerMac G4 for crossing the 1 gigaflop threshold.

Steve Jobs turned it into an ad.

[OpenMed @OpenMed_AI]

6,000,000+ downloads. 3,000+ GitHub stars. All open-source, Apache 2.0.

Thank you to the Codex team at OpenAI for 6 months of Pro, and to @reach_vb for making it happen. It means a lot.

Open medical AI is just getting started. Come build the on-device future with us. 👇

[Jeff Dean @JeffDean]

People replace their phones every ~4 yrs. This means there are hundreds of millions of old phones discarded each year that are still perfectly usable as computing devices. @Google in collabration with @UCSD is exploring how to turn these old phones into cloud-computing “phone clusters”. Putting phones back in service in this way can directly reduce the environmental footprint of computing by avoiding the need for further raw material extraction, and taking advantage of the embodied carbon already incurred from manufacturing these devices, and modern phones actually are already quite powerful computers. Read more in the blog below ⬇️

[Andrew Ambrosino @ajambrosino]

we shipped the Tibo button

[Ygor Lemos @ygbr]

So Fable 5 is xenophobic by design...

[Ygor Lemos @ygbr]

@AnthropicAI this is disrespectful and imbecile... you should fight for your users rights...

[Ygor Lemos @ygbr]

@AnthropicAI @claudeai regarding this: https://t.co/BIhIaCcBbf

[Ygor Lemos @ygbr]

This is the kind of thing that will make @AnthropicAI and @claudeai eventually fall... This is governamental bullshit on top of technology access with imbeciles imposing rules everywhere.... Hope open source models catchup soon and I can run locally everything that I need.... fucking retard move

[ClaudeDevs @ClaudeDevs]

New for Apple developers: Foundation Models support for Claude lets developers use Apple's Foundation Models framework to call Claude for multi-step reasoning, code generation, and longer context.

[Awni Hannun @awnihannun]

It's very cool that Apple shipped a 20B parameter on-device.

You can't put 20B parameters in RAM at any reasonable precision. To make it work they are using pretty exotic architecture by today's standards.

A small model predicts from the query (or prompt) which experts to load from Nand into RAM. The key distinction from a typical MoE is that you do this once per query and then generate all the tokens with the same experts (instead of switching the experts for every token).

[Dark Web Informer @DarkWebInformer]

🚨🇧🇷MASSIVE CLAIM🇧🇷🚨

A threat actor known as BuddhaGroup is advertising a dataset allegedly tied to Brazil's Receita Federal (Federal Revenue Service), claiming to sell a complete citizen database said to be extracted directly from official sources.

The actor claims the dataset covers roughly 248 million Brazilian citizens and totals approximately 1.07 billion records across 24 SQLite files. Listed tables allegedly include a master person table (290M rows) with names, type, and email; full addresses (290M rows); individual records (248M rows) with CPF, birth date, sex, mother's name, and occupation; phone numbers (133M rows); company CNAE codes; legal entities with CNPJ; and partner and shareholder records.

A detailed schema for each table has been posted, and samples are said to be available. Pricing is hidden behind a spoiler tag.

Claim is unverified.

💥 Stop guessing what's redacted. Paid subscribers see everything: https://t.co/281Qjc6p2J

[Ygor Lemos @ygbr]

.@claude
.@ClaudeDevs
.@AnthropicAI

Mac crashes and freezes continues to grow, "im constantly updating the gh issue to reflect what I'm experience... you guy truly need e native app with proper map spawning , memory and cpu control

https://t.co/feg5dlzslQ

[Ygor Lemos @ygbr]

@Japheth https://t.co/feg5dlzslQ

[Ygor Lemos @ygbr]

@noahelhadedy @claudeai https://t.co/feg5dlzslQ

[Ygor Lemos @ygbr]

@MicahBerkley @AnthropicAI @ClaudeDevs https://t.co/feg5dlzslQ

[Sawyer Merritt @SawyerMerritt]

Starlink V3 satellites

Bandwidth per Satellite:
• V2: 96 Gbps
• V3: 1,024 Gbps

Bandwidth per Launch:
V2: 2,600 Gbps
V3: 61,000 Gbps

Deployment per Launch:
• V2: 27 satellites (on Falcon 9)
• V3: 60 (on Starship)

Starlink V3 satellites will begin to be deployed in late 2026 on Starship.

[Ygor Lemos @ygbr]

😂 No!

https://t.co/hgZ99suDkB