-
2024-05-14
OpenAI's RLHF Specifications
-
2024-05-02
RLHF: A thin line between useful and lobotomized
-
2024-04-30
Phi 3 and Arctic: Outlier LMs are hints
-
2024-04-24
AGI is what you want it to be
-
2024-04-21
Llama 3: Scaling open LLMs to AGI
-
2024-04-18
Stop "reinventing" everything to "solve" AI alignment
-
2024-04-16
The end of the "best" open LLM
-
2024-04-03
Why we disagree about what open-source AI is
-
2024-03-29
DBRX: The new best open LLM and Databricks' ML strategy
-
2024-03-22
LLM RLHF Evaluations: Trust, performance, and price (bonus, announcing RewardBench)
-
2024-03-13
LLM commoditization and product moats
-
2024-03-06
Defining an open-source LLM
-
2024-03-04
Interviewing Louis Castricato of Synth Labs, Eleuther AI on RLHF, Gemini Drama, DPO, Carper AI
-
2024-02-28
How to cultivate a high-signal AI feed
-
2024-02-23
Google ships it: Gemma open LLMs and Gemini backlash
-
2024-02-20
10 Sora and Gemini 1.5 follow-ups code-base in context, deepfakes, pixel-peeping, inference costs...
-
2024-02-17
Releases! OpenAI’s Sora for video, Gemini 1.5's infinite context, and a secret Mistral model
-
2024-02-14
Why reward models are still key to understanding LLM alignment
-
2024-02-07
Alignment-as-a-Service upstarts taking on Scale AI
-
2024-02-01
Open Language Models (OLMos) and the LLM landscape
-
2024-01-30
Model merging lessons in The Waifu Research Department
-
2024-01-24
Local LLMs, some facts some fiction
-
2024-01-17
Multimodal blogging: My AI tools to expand your audience
-
2024-01-10
Multimodal LM roundup: Unified IO 2, inputs and outputs, Gemini, LLaVA-RLHF, and RLHF questions
-
2024-01-05
Where 2024's "open GPT4" can't match OpenAI's
-
2024-01-03
It's 2024 and they just want to learn
-
2023-12-29
Interconnects year in review: 2023
-
2023-12-21
Interviewing Tri Dao and Michael Poli of Together AI on the future of LLM architectures
-
2023-12-14
Big Tech's LLM evals are just marketing
-
2023-12-12
Mixtral: The best open model, MoE trade-offs, release lessons, Mistral raises $400mil, Google's loss
-
2023-12-06
The DPO debate: Do we need RL for RLHF?
-
2023-12-04
Synthetic data: Anthropic’s CAI, from fine-tuning to pretraining, OpenAI’s Superalignment, tips, ...
odevtube: YouTube for Developers
