Comment: Morning dealio
Transcript: So this morning I woke up, had a great cup of coffee, probably one of the best cups I've made so far, and I fixed the zig build for my PR for llama.cpp. Hopefully that will go through today or tomorrow. And now I am working on my project, fixing a bunch of small things that I noticed. The first thing is adding user data into captions and summaries, and that's done. So that should help fairly significantly, I would say. And then now I'm, like, I noticed a bad transcription, and it honestly seems like OpenAI's fault, because I'm, well, in the sense, like, their API is using Whisper V2, and I'm running Whisper V3 on llama.cpp, which gets the correct transcription. So yeah, that's kind of what it is.
85.43% similar
The user had an eventful day, involving work and some leisure activities. They worked on llama.cpp, fixed some GitHub issues, and implemented a saving function for a project. They also discussed plans for future improvements, including creating a caching mechanism, improving code generation, and implementing a logging system for transformations. They aim to enhance the development experience and bridge the gap between computer and human perspectives. The user expressed satisfaction with completing the caching task. The user discussed their internal struggle between choosing to do the simple thing versus the more complex thing, ultimately deciding on the simple approach. They also mentioned distraction related to financial concerns and expressed interest in creating things for Vision Pro and exploring augmented reality.
84.18% similar
I woke up at 6 and got straight to work on my Llama.cpp, made some changes, and submitted them for review, hoping for acceptance and a merge. After work, I'm heading to Tourmaline to surf despite the mild rainy weather. Upon returning, I plan to relax, possibly finish Kyle's sweatshirt, meditate, do some shopping, and clean up my code, which I currently consider subpar. I intend to tackle some easy tasks on my to-do list to smooth out any issues and improve my code's overall quality.
83.83% similar
The speaker is focused on their API project and mentioned the stable diffusion model. They have also worked on running and testing various local language models, including Whisper and Orca 7 billion. They are curious to wire the models as a pipeline step and compare the output with GPT. The speaker is unsure of the success of their API project and the effectiveness of the language models, but they express eagerness to explore and experiment further.
Yesterday was a pretty good and productive day for me. In the morning, I was at work, really diving deep into what's possible with the backend, especially focusing on modal and non-real-time transcriptions—successfully managing to make them work. I'm considering extending that setup to my local machine to ensure it optimally selects the best backend for serving content. I also thought about exploring Olama for similar functionalities but realized I might need to handle streaming code specifically. There's a part of me thinking about delving into `whisper.cpp` because I believe streaming support is achievable without excessive effort, though it might require some C++ handling. Enhancing Python and node bindings, especially making GGML usable like a tensor library in Python, is another aspect I’m looking into. Aside from work, I managed to meditate for 15 minutes, skipped breakfast but enjoyed beans and rice for lunch, and had Kyle, Claire, Kyle's dad, and Miri over for lunch and later for games, playing the crew, which was quite enjoyable. Claire brought dessert, and I made some pasta and chicken for dinner. My fascination with O1 or Open Interpreter continues, and I'm eager to explore more about it. For today, I'm considering going surfing if the situation allows, based on what I manage to accomplish in the morning and my energy levels through the day. I'm planning to start my day with meditation—trying it before my coffee—to see how that feels and take the day from there.
In the first bucket, the focus is on achieving AI-level parallelism, creating a better pipeline, enabling the execution of different LLM tasks in parallel, and allowing future agents to add information to an execution graph. This parallelization is crucial for distributed systems processing and likely to advance the distribution and parallel running of models. The second bucket involves implementing transformations, such as converting unstructured transcripts into organized bullet point lists, and making this adaptable and viable through JSON. The goal is to seamlessly convert text into a GitHub issue, providing instructions for transformation and capturing context to refine models.
81.72% similar
The author contemplates the process of converting an audio note into a transcript, then summarizing it on their "burrito" page. They express a desire to adjust the summarization voice to better represent themselves on the page. Recognizing that this feature may not have widespread appeal, the author nonetheless sees value in providing users with controls to personalize their "burrito." The concept of allowing users to fine-tune their experience is seen as an intriguing possibility.
79.79% similar
The speaker is reflecting on their experience with making audio burrito posts, noting that it often requires multiple attempts to get into the correct mindset—similar to drafting written posts. They're grappling with the challenge of monologuing without a clear understanding of the audience, as they are aware that at least John and CJ will hear it, but uncertainty about the wider audience affects their ability to communicate effectively. This creates a 'contextual membrane shakiness' as the speaker finds the lack of audience boundaries difficult to navigate, which they recognize may vary among different people. The speaker concludes by deciding to end the current note and start a new one.
78.48% similar
Pascal, from Brooklyn, is excited to engage with a new social network and a burrito he just tried. He's currently experiencing winter weather and has consumed a weed gummy before diving into work on the Tanaki app with multiplayer live video features. He plans to get a massage to unwind physically and mentally. Pascal hopes for a feature that enables connection with his audience to avoid feeling isolated and looks forward to interacting with others on the platform.
77.44% similar
The speaker conveys their frustration with a difficult fundraising experience, describing a particularly unsatisfactory video call with a fund representative. The caller was in a bad mood, hadn't reviewed the provided materials, and hesitated to engage with the product's features. This led to a tense exchange where the speaker challenged the representative's commitment to valuing founders versus purely focusing on financial metrics. Feeling disillusioned, the speaker is left with a distaste for these disengaged "NPCs" and remains focused on their vision of fostering creative and engaging spaces.