@corbtt @dvdcrbt can give concrete examples, but from my experience, they enable completely different things. RAG/search really just gives the model *info* to work with. Fine-tuning changes the *behavior* of the model.
LLMS
-
GPT-OSS Chat Template Special Tokens Analysis
By
–
Wow gpt-oss has a very interesting chat template Special tokens for "channel" (analysis, commentary, final) and "constrain". Still pretty ChatML-like!
-
OpenAI Open Weights Models Outperform Earlier Generation AI
By
–
The OpenAI open weights models are very impressive. These basically beat every model from eight months ago & the small one runs on a laptop. For example, when HLE came out in January, the top score was 3-4%. Been playing with the models and so far they feel like their scores.
-
Stealth AI Models Outperform Open Source Models on WebArena
By
–
Ha habido mucha especulación en las últimas semanas sobre si los modelos furtivos aparecidos en el WebArena serían los modelos open source pero al parecer no. Aquellos rendían mejor. https://t.co/tZ5SaLGSXy
— Carlos Santana (@DotCSV) 5 août 2025Ha habido mucha especulación en las últimas semanas sobre si los modelos furtivos aparecidos en el WebArena serían los modelos open source pero al parecer no. Aquellos rendían mejor.
-
Open Source LLMs and RL Boost AI Product Margins
By
–
One super important point: for companies using LLMs at scale, the new open source OpenAI models, combined with RL from folks like @OpenPipeAI
, will dramatically improve margins on AI products! -
OpenAI Open Source Models 120B and 20B MoE Tested
By
–
A quick test of the @OpenAI new open source models: 120b and 20b MoE models. With the @FeatureCrewPod planet generation prompt
— Peter Gostev (@petergostev) 5 août 2025
The comparison is to the best one I've seen – a yet unreleased OpenAI model, but then Sonnet 4, Kimi K2, Qwen 3 Coder and GLM-4.5 for comparison. The… pic.twitter.com/a4bh1WclKVA quick test of the @OpenAI new open source models: 120b and 20b MoE models. With the @FeatureCrewPod planet generation prompt The comparison is to the best one I've seen – a yet unreleased OpenAI model, but then Sonnet 4, Kimi K2, Qwen 3 Coder and GLM-4.5 for comparison. The
-
GPT-5 Release Imminent as OpenAI Open-Source Model Launches
By
–
Étant donné la sortie du nouveau modèle GPT-OSS ce soir, je pense qu'Altman a un plan de secours. Il ne l’aurait pas autorisé sinon. Ça sent l’arrivée imminente de GPT-5. Des fuites commencent aussi à émerger. Un important partenaire d’OpenAI, Flowith qui héberge leurs
-
OpenAI Launches GPT-OSS Pro Mode for Enhanced Open Source
By
–
Introducing `gpt-oss Pro Mode`!
— Matt Shumer (@mattshumer_) 5 août 2025
Basically o3 Pro, but for the new OpenAI open source models 🙂
Pro Mode chains together up to 10 instances of the new OpenAI GPT-OSS model, enabling it to produce a better answer than one instance alone could create!
Open source, link here: pic.twitter.com/rWa3GZBYpjIntroducing `gpt-oss Pro Mode`! Basically o3 Pro, but for the new OpenAI open source models 🙂 Pro Mode chains together up to 10 instances of the new OpenAI GPT-OSS model, enabling it to produce a better answer than one instance alone could create! Open source, link here:
-
OSS Models Now Available on Flowise via Multiple Providers
By
–
Welcome to the OSS, use them now on Flowise via Groq, Ollama, Fireworks, TogetherAI, LocalAI and more!
— FlowiseAI (@FlowiseAI) 5 août 2025
More testing on the way🤓 https://t.co/DUnOK2yyBS pic.twitter.com/GNTQ6059lmWelcome to the OSS, use them now on Flowise via Groq, Ollama, Fireworks, TogetherAI, LocalAI and more! More testing on the way
-
OpenAI Releases ‘Harmony’ Format for Building on Open-Weight Models
By
–
On top of new open-weight models, OpenAI open sourced “Harmony” format for developers to help building on top of GPT-OSS. “The format is designed to mimic the OpenAI Responses API, so if you have used that API before, this format should hopefully feel familiar to you.”