Results
188 articlesSort
11:05EN
Matthew Berman· Nov 7, 2023Testing Dolphin 2.2, a Mistral 7B Fine-TuneMatthew Berman · Forward FutureMatthew Berman tries a small open-weight model on coding, formatting and reasoning prompts, with mixed results.
6:40ENMatthew Berman· Oct 27, 2023Running MemGPT with an Open-Weight Model on RunPodMatthew Berman · Forward FutureMatthew Berman connects the original MemGPT project to a model served through text-generation-webui, then tests a simple memory interaction. The demonstration uses a remote GPU and historical software versions.
7:02ENMatthew Berman· Oct 18, 2023Connecting AutoGen to a RunPod-Hosted Model with Text Generation WebUIMatthew Berman · Forward FutureIn a 2023 walkthrough, Matthew Berman connects AutoGen to Dolphin 2.1 Mistral 7B through an OpenAI-compatible API and tests a small coding task.
4:42ENMatthew Berman· Oct 17, 2023Connecting AutoGen to a Local Model With LM StudioMatthew Berman · Forward FutureMatthew Berman demonstrates an early local-model setup and explains where agent behavior still needs work.
1:14:36EN
Cognitive Revolution "How AI Changes Everything"· Oct 13, 2023PodcastZulu Bypasses GPT-4, and a Hundred Examples Undo the GuardrailsHost Nathan LabenzNathan Labenz reads seven papers — four hopeful, three not — on whether anyone can actually keep a language model under control.
1:04:38EN
Lex Fridman· Sep 28, 2023Podcast · 2 speakersHundreds of Miles Apart, Zuckerberg and Fridman Sat Close Enough to See the WrinklesGuest Mark Zuckerberg · Host Lex FridmanLex Fridman sat in a dark room in Austin wearing a Quest headset; Mark Zuckerberg sat in another conference room, also wearing one, and it did not feel like a video call.
29:38EN
No Priors: AI, Machine Learning, Tech, & Startups· Sep 21, 2023Podcast · 2 speakersA Beginner Just Shipped a $250K Business. Professionals Got 30 Percent.Host Sarah Guo, Elad GilReplit CEO Amjad Masad on Ghostwriter, why a 3-billion-parameter model was enough, and the agents he wants earning bounties while you sleep.
12:49ENMatthew Berman· Sep 14, 2023Falcon 180B: A 2023 Review of TII’s Open-Weight ModelMatthew Berman · Forward FutureMatthew Berman tests coding, reasoning and writing prompts while examining the model’s training scale and license.
30:03ENNo Priors: AI, Machine Learning, Tech, & Startups· Sep 7, 2023Podcast · 2 speakersA Dinner-Plate Chip Cut Training From 60 Days to 3.5Host Sarah Guo, Elad GilCerebras CEO Andrew Feldman tells No Priors why wafer-scale silicon, not another GPU, is the answer to the compute crunch — and why most production models will stay at 13 billion parameters or below.
10:20ENMatthew Berman· Aug 30, 2023Phind Code Llama 34B vs GPT-4: A 2023 Python Coding TestMatthew Berman · Forward FutureMatthew Berman compares a quantized Phind fine-tune with GPT-4 on games, short functions and refactoring, with mixed results.
52:48ENCognitive Revolution "How AI Changes Everything"· Aug 25, 2023PodcastOpenAI Cut Fine-Tuning 90 Percent, and Founders Crossed Llama 2 Off the ListHost Nathan LabenzNathan Labenz and Erik Torenberg walk through GPT-3.5 Turbo fine-tuning, why self-hosting still loses on total cost, and what is actually working in code, school, and medicine.
10:22ENMatthew Berman· Aug 4, 2023Matthew Berman on Llama 2, AI Tools, Robots, and the LK-99 ClaimMatthew Berman · Forward FutureA 2023 AI news roundup covers open-weight models, synthetic influencers, tool use and robotics, alongside an early superconductivity claim that later research challenged.
9:46ENMatthew Berman· Jul 17, 2023Orca Mini V2 vs. OpenOrca: A 2023 Informal Model ComparisonMatthew Berman · Forward FutureMatthew Berman tests two Orca-inspired models on coding, writing and reasoning, with results shaped by prompt setup and subjective scoring.
12:20ENMatthew Berman· Jul 10, 2023Testing UltraLM 13B: A Small Model’s Strengths and Reasoning ErrorsMatthew Berman · Forward FutureA 2023 local test finds useful writing and simple coding alongside failures in games, arithmetic and logic.
18:08ENMatthew Berman· Jun 29, 2023Six Language Models Compared on an Informal 2023 Prompt SetMatthew Berman · Forward FutureMatthew Berman tests coding, writing and reasoning with H2O GPT, finding a tie under a small and subjective rubric.
7:21ENMatthew Berman· Jun 26, 2023Testing Orca Mini 13B, an Unofficial Model Inspired by OrcaMatthew Berman · Forward FutureMatthew Berman loads a quantized Orca Mini 13B and tries coding, reasoning, arithmetic, and summarization prompts. His 2023 informal test produces several failures and a few successes.
8:17ENMatthew Berman· Jun 22, 2023Using OpenLLM to Serve Open Models Through an APIMatthew Berman · Forward FutureMatthew Berman demonstrates a local model server, its interactive API and a Python client in a 2023 walkthrough.
4:36ENMatthew Berman· Jun 20, 2023Testing WizardCoder 15B as a Local Coding AssistantMatthew Berman · Forward FutureMatthew Berman runs the 2023 WizardCoder model locally, testing small Python exercises and a longer Snake game.
59:28ENCognitive Revolution "How AI Changes Everything"· Jun 16, 2023PodcastFrom $500,000 to $50,000: MosaicML Made Training Your Own Model a Priced ProductHost Nathan LabenzJonathan Frankle and Abhi Venigalla explain who is training custom LLMs, why extraction beats chat, and how ALiBi stretches a 65k context window.
10:23ENMatthew Berman· Jun 15, 2023Testing Hosted Falcon 40B and Document Chat in h2oGPTMatthew Berman · Forward FutureMatthew Berman tries H2O.ai’s 2023 hosted Falcon 40B interface on coding, writing and reasoning prompts, then demonstrates document chat.
19:38ENMatthew Berman· Jun 9, 2023Orca: Teaching a Smaller Model with GPT-4 ExplanationsMatthew Berman · Forward FutureMatthew Berman reviews Microsoft Research’s 2023 Orca paper and its approach to training a 13-billion-parameter model on detailed teacher responses.
2:41:58ENLex Fridman· Jun 8, 2023Podcast · 2 speakersZuckerberg showed up as Mark Elliott — then argued for many AIs, not oneGuest Mark Zuckerberg · Host Lex FridmanOn his second Lex Fridman podcast, the Meta CEO treats a disguised first jiu-jitsu tournament, an open research model called LLaMA, and a future of many agents as the same bet: ship before it is perfect, and do not build a single god model.
10:40ENMatthew Berman· Jun 7, 2023Testing Nous Hermes 13B Locally: Mixed Reasoning and Unsafe ResponsesMatthew Berman · Forward FutureMatthew Berman compares a 2023 quantized model on hosted and local hardware, with uneven results across coding, logic and safety.
8:51ENMatthew Berman· Jun 2, 2023Falcon 40B: A 2023 Leaderboard Result and a Slow GPU TestMatthew Berman · Forward FutureMatthew Berman tries a quantized Falcon 40B Instruct checkpoint on a hosted GPU and finds useful output but slow generation.Load moreShowing 24 of 188