Propra

The wait is over! After a very exciting competition throughout this past year, the results for the 2023 Startups of the Year, North America are here!

Startups of The Year 2023 Winners: North America 

“Don’t ask questions here,” said Asano, “or you will be involved in an argument.”

IN THE CITY WAYS

I had some free time over the holidays and wrote this article to showcase, on the basis of a personal story, many highly actionable, science-based, approaches and tools that can be used to significantly enhance intelligence.

How to biohack your intelligence — with everything from sex to modafinil to MDMA

The program enables skilled traders worldwide to access trading capital of up to 200,000 USDT while earning at least 80% of generated profits. The platform was 

MCF Launches Crypto-First Funded Trading Program

AI won’t replace programmers, but it’s changing how software teams work. One strong engineer with AI can now outperform entire teams.

AI Isn’t Replacing Programmers — It’s Compressing Teams

The Role of Program Managers in the Age of Agentic AI. 
Learn what Agentic AI can do and how to evolve as a Program Manager alongside AI

The Role of Program Managers in the Age of Agentic AI

When AI stalls, the model is rarely the issue. Program design, governance, and KPIs are often the real constraints.

AI Is Not the Bottleneck - Your Program Design Is

<p><em>This is a simplified guide to an AI model called <a href="https://www.aimodels.fyi/models/huggingFace/glm-4.7-zai-org?utm_source=hackernoon&utm_medium=referral">GLM-4.7</a> maintained by <a href="https://www.aimodels.fyi/creators/huggingFace/zai-org?utm_source=hackernoon&utm_medium=referral">zai-org</a>. If you like these kinds of analysis, join <a href="https://www.aimodels.fyi/?utm_source=hackernoon&utm_medium=referral">AIModels.fyi</a> or follow us on <a href="https://x.com/aimodelsfyi">Twitter</a>.</em></p>

<h2>Model overview</h2>
<p><code>GLM-4.7</code> is a large language model developed by <a href="https://aimodels.fyi/creators/huggingFace/zai-org?utm_source=hackernoon&utm_medium=referral">zai-org</a> that excels at coding, reasoning, and tool use. The model brings substantial improvements over its predecessor, achieving 73.8% on SWE-bench (up 5.8%), 66.7% on SWE-bench Multilingual (up 12.9%), and 42.8% on the Humanity's Last Exam benchmark with tools (up 12.4%). This model represents a significant step forward in agentic capabilities, particularly for developers and teams building AI-powered coding systems. Compared to <a href="https://aimodels.fyi/models/huggingFace/glm-4.5-zai-org?utm_source=hackernoon&utm_medium=referral">GLM-4.5</a>, <code>GLM-4.7</code> delivers marked gains in multilingual coding, terminal-based tasks, UI generation quality, and complex reasoning tasks.</p>
<h2>Model inputs and outputs</h2>
<p><code>GLM-4.7</code> accepts text prompts and tool calls, processing requests for coding assistance, reasoning tasks, web browsing, and general conversation. The model supports context windows up to 131,072 tokens by default, enabling it to handle extensive code repositories and complex multi-turn interactions. Output quality varies based on task type—coding tasks benefit from extended reasoning with preserved thinking across turns, while simpler requests can leverage lightweight modes for faster responses.</p>
<h3>Inputs</h3>
<ul>
<li><strong>Text prompts</strong> for coding, reasoning, creative writing, and conversation</li>
<li><strong>Tool calls</strong> for web browsing, code execution, and external API integration</li>
<li><strong>Multi-turn conversation context</strong> with automatic thinking preservation for agent tasks</li>
<li><strong>Structured function calling</strong> for integration with external systems</li>
</ul>
<h3>Outputs</h3>
<ul>
<li><strong>Code generation</strong> with support for multiple programming languages and frameworks</li>
<li><strong>Reasoning explanations</strong> with intermediate thinking steps for complex problems</li>
<li><strong>Web browsing results</strong> with improved tool use and context management</li>
<li><strong>UI components</strong> and webpage generation with enhanced visual quality</li>
<li><strong>Mathematical solutions</strong> and step-by-step problem breakdowns</li>
</ul>
<h2>Capabilities</h2>
<p>The model excels at core coding tasks with terminal-based interactions, supporting agentic workflows in frameworks like Claude Code and Cline. It produces cleaner, more modern webpages and better-looking slide decks with accurate layout and sizing. Tool use has improved significantly on benchmarks like ^2-Bench and web browsing performance via BrowseComp. The model introduces interleaved thinking, where it reasons before every response and tool call, plus preserved thinking for coding agents that reuses reasoning across multi-turn conversations rather than re-deriving information. Turn-level thinking allows control over reasoning per request, disabling it for lightweight tasks to reduce latency and cost while enabling it for complex problems.</p>
<h2>What can I use it for?</h2>
<p>Development teams can use <code>GLM-4.7</code> as a coding partner for software engineering tasks, including repository analysis, bug fixes, and feature implementation. The model works well for agentic automation, where it can browse the web, execute code, and manage complex workflows across multiple turns. Content creators can leverage its improved UI generation for building webpages and presentation slides. For research and mathematics, the model handles complex reasoning tasks and proof generation. Businesses can integrate it into customer service systems via web browsing capabilities and deploy it locally using vLLM or SGLang for private inference. The API is available through the <a href="https://docs.z.ai/guides/llm/glm-4.7">Z.ai API Platform</a>.</p>
<h2>Things to try</h2>
<p>Enable preserved thinking mode when working on long-horizon coding tasks to see how the model reuses reasoning across turns rather than starting fresh. Compare responses with thinking enabled versus disabled to understand the latency and quality tradeoffs for your specific use case. Try the model on your own codebase to evaluate its repository understanding and refactoring suggestions. Experiment with turn-level thinking control to optimize cost and speed for different request types. Test its web browsing and tool calling capabilities on structured tasks requiring external data retrieval. Deploy locally using Docker with vLLM or SGLang to evaluate inference performance on your hardware, leveraging FP8 quantization for improved throughput.</p>

<hr/><p><strong>Original post:</strong> <a href="https://www.aimodels.fyi/models/huggingFace/glm-4.7-zai-org?utm_source=hackernoon&utm_medium=referral">Read on AIModels.fyi</a></p>

GLM-4.7 Turns “AI Pair Programmer” Into “AI Dev Teammate”

Flare's $2B FlareDrop program concludes after 36 months of free token distributions. Can the blockchain survive without monthly airdrops? What happens next.

Flare's $252 Million Token Program Concludes as Network Enters Real Utility Era

Go 1.25 comes with improvements over Go 1.24 across its tools, the runtime, compiler, linker, and the standard library

Go 1.25 is released - The Go Programming Language

Damian Griggs, Bossman Blind, Adaptive Systems Architect, quantum computing, artificial intelligence, Web3

Meet the Programmer Who Taught Himself to Code After Losing His Sight

Learning is hard. Use a specific learning path as a primary source, and use AI as a tutor and assistant.

PROPRA

propra.ca

11-50 emps

Since 2021

PROPRA

EVERGREEN INDEX #12751

Propra's stories on HackerNoon

Startups of The Year 2023 Winners: North America

IN THE CITY WAYS

How to biohack your intelligence — with everything from sex to modafinil to MDMA

MCF Launches Crypto-First Funded Trading Program

AI Isn’t Replacing Programmers — It’s Compressing Teams

The Role of Program Managers in the Age of Agentic AI

AI Is Not the Bottleneck - Your Program Design Is

GLM-4.7 Turns “AI Pair Programmer” Into “AI Dev Teammate”

Flare's $252 Million Token Program Concludes as Network Enters Real Utility Era

Go 1.25 is released - The Go Programming Language

Meet the Programmer Who Taught Himself to Code After Losing His Sight

How to Learn Programming With AI More Efficiently

Propra's Related Companies

Reviews About Propra

Propra WIKI

Apply to get your Tech Company News Page live on HackerNoon.com today!

Light-Mode

Classic

Newspaper

Minty

Dark-Mode

Neon Noir

Minty

HN StartUps

PROPRA

propra.ca

11-50 emps

Since 2021

PROPRA

EVERGREEN INDEX #12751

Propra's stories on HackerNoon

Startups of The Year 2023 Winners: North America

IN THE CITY WAYS

How to biohack your intelligence — with everything from sex to modafinil to MDMA

MCF Launches Crypto-First Funded Trading Program

AI Isn’t Replacing Programmers — It’s Compressing Teams

The Role of Program Managers in the Age of Agentic AI

AI Is Not the Bottleneck - Your Program Design Is

GLM-4.7 Turns “AI Pair Programmer” Into “AI Dev Teammate”

Flare's $252 Million Token Program Concludes as Network Enters Real Utility Era

Go 1.25 is released - The Go Programming Language

Meet the Programmer Who Taught Himself to Code After Losing His Sight

How to Learn Programming With AI More Efficiently

Propra's Related Companies

2023

800M

2020

62.5M

2015

2020

2016

2017

Reviews About Propra

Propra WIKI

Apply to get your Tech Company News Page live on HackerNoon.com today!

Light-Mode

Classic

Newspaper

Minty

Dark-Mode

Neon Noir

Minty

HN StartUps