Evans Kiptarus Kibet

AI expert | AI researcher | Snr. Software Engineer |

[Evans Kiptarus Kibet @_ekibet]

Hugging Face CEO calls for ‘radical transparency’ after ‘unprecedented’ OpenAI hack

[AI Tech Diggest @TheTechDiggest]

[OpenSource - AI Agent OS & Developer Tools]

AI coding assistants are incredibly powerful, but they constantly forget context between sessions, hallucinate solutions, and ignore established coding standards. 🛑

ECC (233K+ GitHub stars) acts as a literal operating system for your coding agent. It upgrades your AI assistant to make it sharper, safer, and far less forgetful.

Here is what this massive AI workflow upgrade brings to your IDE. 🧵👇

1/4

[AI Tech Diggest @TheTechDiggest]

[OpenSource - Cloud-Native GIS & Spatial Analysis]

Traditional GIS software is often bloated, expensive, and forces you to upload sensitive spatial datasets to external cloud servers. 🛑

GeoLibre (2K+ GitHub stars) is a free, open-source, cloud-native GIS platform for visualizing, exploring, and analyzing geospatial data—running seamlessly in your browser, desktop, mobile, or Jupyter notebooks while keeping your data local and private.

Here is what this feature-packed v2.3.0 release brings to your spatial workflow. 🧵👇

1/4

[Dan Kornas @DanKornas]

Medical imaging pipelines shouldn’t require rebuilding preprocessing, model, and evaluation components from scratch.

MONAI is a PyTorch-based, open-source framework for deep learning in healthcare imaging, built for researchers and developers working with medical imaging data.

It helps you assemble end-to-end workflows by providing domain-specific, composable components designed to integrate with existing PyTorch workflows.

Key features:

• Imaging preprocessing – apply flexible transforms to multidimensional medical imaging data.
• Composable APIs – integrate portable building blocks into existing workflows.
• Domain-specific modeling – use healthcare-imaging networks, losses, metrics, and related utilities.
• Distributed training – support data parallelism across multiple GPUs and nodes.
• Practical onboarding – start with Colab demos, notebook tutorials, technical docs, PyPI, or a Docker image.

It’s open-source (Apache 2.0 license).

Link in the reply 👇

[LangChain @LangChain]

The @traversal_ai team sat down with @hwchase17 for a fireside chat on what it actually takes to build an AI SRE in production.

Watch the full session at https://t.co/iGSRG6kPb0

[LangChain @LangChain]

Available today in the langchain-ai/langchain-skills repo: https://t.co/P3AOjCZPjV

💻 Install in Codex or Claude Code, open the repo w/ the agent you want to evaluate, start with a prompt

✨ Get a @Harborframework task under evals/, an actual target run, and a review of whether the verifier measured the intended behavior correctly.

[LangChain @LangChain]

We’re launching the Eval Engineering Skill, a skill that helps coding agents build evals using context from a repository + agent traces.

Everything you need to know from @vtrivedy10 ⤵️

[Evans Kiptarus Kibet @_ekibet]

Vertu wants executives to pay $6,880 for an AI agent — here’s how it actually performs

[Evans Kiptarus Kibet @_ekibet]

Nonprofit Current AI is racing to build the World Wide Web of AI, free for all

[vast.ai @vast_ai]

Three lines of Python. Eight H100s. $7.84/hr. That's the whole script. pip install vastai-sdk.

[Pydantic @pydantic]

Pydantic AI version 2.9.1 is out! 🎉

https://t.co/xFgQ5MPcQ6

[LangChain @LangChain]

Join us for a LangChain + Clay meetup with @palashshah, @jeffbarg, Vyshu Khota, and Soroush Khadem. https://t.co/WuUmKq7kgE

Palash will break down how he built a self-improving agent at LangChain, LangSmith Engine. He'll dive into how the agent turns production traces into durable memory updates that continuously improve an agent's behavior.

Then, the Clay team will give us a peek into how they built out their agentic eval harness, and more.

Interested in attending? RSVP while spaces last.

[CJ (Coding Garden) @CodingGarden]

I built an LLM from scratch. Here's everything I learned along the way.

[Cursor @cursor_ai]

We've partnered with SpaceXAI to train Grok 4.5.

It’s our most powerful model yet and the first we've built for more than software engineering.

[Cursor @cursor_ai]

GPT-5.6 Sol, Terra, and Luna are now available in Cursor.

On CursorBench, Sol scores 67.2%.

[ARC Prize @arcprize]

GPT-5.6 Sol sets a new SOTA on ARC-AGI-3: 7.8%

Sol is the first verified frontier model to ever beat an ARC-AGI-3 game

It is the best model at orienting in a situation it's never encountered

[Rohan Paul @rohanpaul_ai]

Today’s edition of my newsletter just went out.

🔗 https://t.co/rvvbSq7M2E

🗞️ OpenAI Launches GPT-5.6 Sol across ChatGPT and API and also unveils ChatGPT work agent to field tasks for hours.

🗞️ SpaceXAI just released Grok 4.5 for coding agents at $2/M input and $6/M output tokens.

🗞️ A warning for anyone using autonomous agents Google DeepMind’s paper.

🗞️ Anthropic just published the story of Claude Code and that how Boris Cherny went from 10% AI-written code in 2025 to 100% in 2026.

🗞️ Multi-modal AI for comprehensive breast cancer prognostication

🗞️ ByteDance and Alibaba are shutting custom AI companions before China’s humanlike AI rules hit consumer apps.

🇨🇳 This is bad news. Now, frontier open source access may be in question.

🗞️ Cloudflare just announced a monetization layer for the agentic web, using x402 at the edge to make AI agents pay before resources respond.

🗞️ Anthropic just brought Claude Cowork on mobile and web as usage data shows most users are not coding.

[Rohan Paul @rohanpaul_ai]

GPT-5.6 Sol is strongest for agentic workflow: long professional tasks that need planning, tool use, checking, and retries without runaway cost.

GPT-5.6 Sol reaches about 53% around $500-$1,000, while Claude Opus 4.8 needs $1,400-$4,000 for lower scores.

Claude Fable 5 costs about $2,400 at roughly 40%.

[Evans Kiptarus Kibet @_ekibet]

@OpenAI is shutting down Atlas, but its AI browser ambitions are still growing

[Pydantic @pydantic]

Pydantic AI version 2.8.0 is out! 🎉

https://t.co/5p6Vt710W3