nelson black

👨‍💻 Software Engineer- Building SaaS in public

[nelson black @nellicoder]

@nduatirobert_ Get a set of business pain points , get a business thats willing to use your solution before building -(free at first) , build the solution with that business iteratively, then scale

Our issue is starting the other way round - Solutions In Search of a Problems

[nelson black @nellicoder]

@StanbicKE Hi , am interested, please dm me.

[RT @RT_com]

‘We have a commander-in-chief WHO APPRECIATES AND SUPPORTS OUR MILITARY’ — Fox News

‘What fills in the gap is MY FAITH IN OUR COMMANDER-IN-CHIEF’

[nelson black @nellicoder]

@thdxr Thanks man , blessings upon you 👌

[Z.ai @Zai_org]

Introducing GLM-Image: A new milestone in open-source image generation.

GLM-Image uses a hybrid auto-regressive plus diffusion architecture, combining strong global semantic understanding with high fidelity visual detail. It matches mainstream diffusion models in overall quality while excelling at text rendering and knowledge intensive generation.

Tech Blog: https://t.co/tVpAVsSmxb
Experience it right now: https://t.co/M9UaDtxGoV
GitHub: https://t.co/u7HpXQ1WCJ
API: https://t.co/SOOzRdErVS
Discord: https://t.co/hFcRgVZAqJ

Coming soon to https://t.co/DRCwFHQj1P Chat and GLM Coding Plan.

[nelson black @nellicoder]

@hillarykiptoo_ GLM 4.7 is at per at a much much lower cost @Zai_org

[Luis Batalha @luismbat]

After rewatching Home Alone, I couldn’t stop wondering:

how plausible is the oversleep that leaves Kevin behind?
So I wrote a tiny paper and ran the numbers.

Merry Christmas! 🎄

[Chao Huang @huang_chao4969]

🚀 Our lab just open-sourced DeepTutor - AI-Powered Personalized Learning Assistant

We're actively exploring how agentic AI can assist students and researchers throughout their learning process. DeepTutor brings together research, problem-solving, practice generation, and knowledge management into one system that actually understands your learning context.

🔗 Open Source: https://t.co/Wd8odKIRSn

Core Features of DeepTutor:

- 📚 Smart Document Q&A - Throw in your textbooks, papers, and technical docs. Get detailed answers with proper citations when you ask questions.

- 🎨 Knowledge Visualization & Explanation - Turns complicated concepts into clear visuals and interactive pages that match your learning pace.

- 🎯 Practice Question Generator - Creates quizzes based on your material, and can even mimic the style of real exams you upload.

- 🔬 Deep Research & Idea Generation - Helps with academic research, report writing, and brainstorming. Can handle multiple research topics simultaneously.

[Daily Dose of Data Science @DailyDoseOfDS_]

The Ultimate Toolkit for Working with LLMs!

Transformer Lab lets you train, fine-tune, and chat with any LLM - 100% locally. Enjoy 1-click LLM downloads and a drag-and-drop UI for RAG.

100% open-source.

[nelson black @nellicoder]

@_mohansolo @lukecodez conversation history is always better in a side menu item and not a popup

[Google AI Studio @GoogleAIStudio]

gemini 3 vibe coding hackathon starts now

build your best app to solve a real-world problem across science, health, education or business.

$500,000 in Gemini API credit prizes

competition ends dec 12

[Andrej Karpathy @karpathy]

As a fun Saturday vibe code project and following up on this tweet earlier, I hacked up an **llm-council** web app. It looks exactly like ChatGPT except each user query is 1) dispatched to multiple models on your council using OpenRouter, e.g. currently:

"openai/gpt-5.1",
"google/gemini-3-pro-preview",
"anthropic/claude-sonnet-4.5",
"x-ai/grok-4",

Then 2) all models get to see each other's (anonymized) responses and they review and rank them, and then 3) a "Chairman LLM" gets all of that as context and produces the final response.

It's interesting to see the results from multiple models side by side on the same query, and even more amusingly, to read through their evaluation and ranking of each other's responses.

Quite often, the models are surprisingly willing to select another LLM's response as superior to their own, making this an interesting model evaluation strategy more generally. For example, reading book chapters together with my LLM Council today, the models consistently praise GPT 5.1 as the best and most insightful model, and consistently select Claude as the worst model, with the other models floating in between. But I'm not 100% convinced this aligns with my own qualitative assessment. For example, qualitatively I find GPT 5.1 a little too wordy and sprawled and Gemini 3 a bit more condensed and processed. Claude is too terse in this domain.

That said, there's probably a whole design space of the data flow of your LLM council. The construction of LLM ensembles seems under-explored.

I pushed the vibe coded app to
https://t.co/EZyOqwXd2k
if others would like to play. ty nano banana pro for fun header image for the repo

[SunnyBoss | Product Designer 🐝 @iammSunnyBoss]

Kids' Mobile Coding App

[nelson black @nellicoder]

@tipsformenx And chicken

[NewsForce @Newsforce]

Steve Jobs destroyed the whole Consulting profession.

[nelson black @nellicoder]

@MainNeli_ Alcohol is top on the list of most harmful drugs

[nelson black @nellicoder]

@shl "AI gold rush? 🪓 Spoiler: They’re just selling shovels.

Every 'AI will replace juniors' take is SaaS vendors waiting to bait you as a paying customer to some “AI paid solution”. Follow the $$$—it’s never about the ‘revolution,’ it’s about who’s selling the picks.

[nelson black @nellicoder]

@mougendi @shecyclesnbi reason -Attic

[nelson black @nellicoder]

@KhalifKairo start with the problem, not the solution, our main issue is solutions searching for problems, and at times trying to force-fit solutions to problems