CodeClash

[https://codeclash.ai/] - 2025-12-12 15:53:15 - public:mzimmerm

benchmark, code, good, vibe - 4 | id:1536664 -

Compares writing code, rather than other benchmarks which do mostly git patches.

A new open-weights AI coding model is closing in on proprietary options - Ars Technica

[https://arstechnica.com/ai/2025/12/mistral-bets-big-on-vibe-coding-with-new-autonomous-software-engineering-agent/] - 2025-12-12 11:24:01 - public:mzimmerm

agent, ai, code, good, mistral, open, todo, touse, vibe - 9 | id:1536662 -

A new open-weights AI coding model is closing in on proprietary options - Ars Technica

[https://arstechnica.com/ai/2025/12/mistral-bets-big-on-vibe-coding-with-new-autonomous-software-engineering-agent/] - 2025-12-12 11:23:56 - public:mzimmerm

agent, ai, code, good, mistral, open, todo, touse, vibe - 9 | id:1536661 -

It’s the end of vibe coding, already | InfoWorld

[https://www.infoworld.com/article/4093942/the-end-of-vibe-coding-already.html] - 2025-11-22 11:46:47 - public:mzimmerm

aicode, code, good, program, todo, vibe - 6 | id:1536471 -

Open Port Check Tool -- Verify Port Forwarding on Your Router

[https://canyouseeme.org/] - 2025-09-17 19:22:19 - public:mzimmerm

admin, code, good, home, network, online, playground, port, server, service, test, web - 12 | id:1522883 -

Ubuntu 24.04 | Playgrounds | Killercoda

[https://killercoda.com/playgrounds/scenario/ubuntu] - 2025-09-17 19:13:01 - public:mzimmerm

admin, code, good, linux, online, playground, router, server, service, test - 10 | id:1522882 -

1 hour of online linux for free. Can be used for testing home network from outside.

Who needs GitHub Copilot when you can roll your own AI code assistant at home • The Register

[https://www.theregister.com/AMP/2024/08/18/self_hosted_github_copilot] - 2024-08-26 09:07:40 - public:mzimmerm

ai, code, good, home, ide, intellij, local, model, todo, train - 10 | id:1492807 -

Home - Replit

[https://replit.com/~] - 2024-03-04 11:22:14 - public:mzimmerm

account, code, good, online, repl - 5 | id:1489795 -

Replit is a site where I can run any REPL online. Can be used for AI

deepseek-ai (DeepSeek)

[https://huggingface.co/deepseek-ai] - 2024-03-04 02:24:32 - public:mzimmerm

ai, best, code, deepseek, good, huggingface, instruct, llm, model, newspeak, small - 11 | id:1489786 -

They have the 1.3B version!!! This may be the best to start with Newspeak. Should work train even on huggingcface

deepseek-ai/deepseek-coder-6.7b-instruct · Hugging Face

[https://huggingface.co/deepseek-ai/deepseek-coder-6.7b-instruct] - 2024-03-04 02:13:20 - public:mzimmerm

ai, code, generate, good, llm, model, newspeak, opensource - 8 | id:1489783 -

Another possible model. For coding capabilities, Deepseek Coder achieves state-of-the-art performance among open-source code models on multiple programming languages and various benchmarks.

StarCoder: A State-of-the-Art LLM for Code

[https://huggingface.co/blog/starcoder] - 2024-03-03 23:43:17 - public:mzimmerm

ai, code, generate, good, huggingface, llm, model, newspeak - 8 | id:1489773 -

Article has comparison with other code-LLM models

AI Code Tools: The Ultimate Guide in 2024

[https://codesubmit.io/blog/ai-code-tools/] - 2024-03-03 00:19:57 - public:mzimmerm

ai, code, generate, good, model, tool - 6 | id:1489745 -

AI Code tools : Good summary. Does not talk about which pre-trained model they use. One is gemini (bard) -> alphacode2

Fine-tune a pretrained model

[https://huggingface.co/docs/transformers/training] - 2024-03-02 02:39:40 - public:mzimmerm

ai, bert, code, example, good, huggingface, llm, notebook, progress, train, train-bert-on-yelp, tutorial - 12 | id:1489730 -

Use the Bert model to train on Yelp dataset

BigCode - Playground - a Hugging Face Space by bigcode

[https://huggingface.co/spaces/bigcode/bigcode-playground] - 2023-12-09 16:38:55 - public:mzimmerm

ai, bigcode, code, generate, good, model, newspeak, playground, software, starcoder - 10 | id:1485780 -

Look for models that could be used in Newspeak

yabs.io

Yet Another Bookmarks Service

Search

Results

CodeClash

A new open-weights AI coding model is closing in on proprietary options - Ars Technica

A new open-weights AI coding model is closing in on proprietary options - Ars Technica

It’s the end of vibe coding, already | InfoWorld

Open Port Check Tool -- Verify Port Forwarding on Your Router

Ubuntu 24.04 | Playgrounds | Killercoda

Who needs GitHub Copilot when you can roll your own AI code assistant at home • The Register

Home - Replit

deepseek-ai (DeepSeek)

deepseek-ai/deepseek-coder-6.7b-instruct · Hugging Face

StarCoder: A State-of-the-Art LLM for Code

AI Code Tools: The Ultimate Guide in 2024

Fine-tune a pretrained model

BigCode - Playground - a Hugging Face Space by bigcode

Follow Tags

Export: