A very simple cli tool, consuming basic txt format. You can use it in a second window while waiting for your compilation to finish.

Recently I’ve been also experimenting with defining QA pairs in my note files (in a special section). I then use a custom function in emacs to extract these pairs and push to a file as well as Anki.

Here are some of my own high-level experiences / thoughts:

- Perhaps contrary to popular belief I think vibe coding will bring the best software / system architects. This is due to massively shortened feedback loop between architectural idea and seeing it in action, easiness with which it can be changed, and the ability to discuss it at any moment.

- We’re not really coding anymore. This is a new role, not a role of a senior dev reviewing PRs of junior devs. Devs are just best suited (currently) to take on this new role. I came to realization that if you’re reviewing all generated code in detail you’re doing it wrong. You just shifted bottleneck by one step. You’re still coding. You should skim if the code is in line with your high-level expectation and then make LLM maintain an architecture doc and other docs that describe what and how you’re building (this is the info you should know in detail). You can do audits with another LLM whether the implementation is 100% reflecting the docs, you can chat with LLM about implementation at any moment if you ever need. But you should not know the implementation the way you know it today. The implementation became the implementation detail. The whole challenge is to let go of the old and embrace and search for efficiency in the new setup.

- Connected to the above: reading through LLM outputs is a massive fatigue. You are exhausted after the day, because you read hundreds of pages. This is a challenge to fight. You cannot unlock full potential here if you aim at reading and reviewing everything.

- Vibe coding makes you work on the problem level much more. I never liked the phrase “ideas are cheap”. And now finally I think the tides will turn, ideas are and will be king.

- Devil is in the detail, 100%. People with ability to see connections, distill key insights, communicate and articulate clearly, think clearly, are the ones to benefit.

Hope this is helpful for others.

This was a bit unfortunate. I think there is something in the idea of latent space reasoning.

HRM is inspired by multi-timescale processing in the brain: a slower H module for abstract planning and a faster L module for low-level computation. Both modules are based on self-attention and attempt to model reasoning in latent space.

The repo includes: a) the implementation, b) demo that generates animated GIFs where you can see the model refine its solution step by step, c) results of a small ablation study on what drives performance.

The biggest driver (both accuracy and refinement ability) is *training with more segments* (outer-loop refinement), not the H/L two-timescale split. (This lines up with the ARC Prize team's analysis). This is of course a limited study on a relatively simple task, but I thought the results might be interesting to others.

Repo: https://github.com/krychu/hrm

Curious to hear thoughts - iterative refinement isn't new, but I wonder if the "loop-in-a-loop" forward pass, or varied frequencies, might hint at a useful direction for reasoning in latent space (?)

Comments URL: https://news.ycombinator.com/item?id=45198143

Points: 2

# Comments: 0

Comments URL: https://news.ycombinator.com/item?id=37799957

Points: 2

# Comments: 0

The cases of undefined behavior in the C standard are independent of compiler settings or options.

> If C could have a consistent set of rules …

The C language has a well-defined standard, but the presence of undefined behavior is a deliberate aspect of that standard.

https://github.com/krychu/llama

It runs with the original weights, and gets you to ~4 tokens/sec on MacBook Pro M1 with the 7B model.

I get 1 word per ~1.5 secs on a Mac Book Pro M1.

Good video on "Tree of thoughts" which also reviews / puts it in the context of other methods: https://www.youtube.com/watch?v=ut5kp56wW_4

Completion vs conversational interface is something you can read about in the OpenAI API documentation.

For the remaining things I don't have single specific pointer at hand.

I acknowledge it’s simple, runs on terminal only and lacks bells and whistles. But this is also probably why I use it so much.

I always finish up by asking GPT to test my knowledge with a single-choice questionnaire. What I've observed is that the retention of the material is higher compared to "traditional" techniques. Perhaps the conversation style is more immersive, or perhaps focusing on specific knowledge gaps makes for accelerated / personalised learning.

There is of course the problem of accuracy, but I feel like it's often over-stated. Even if GPT is not correct at times, it often uncovers concepts and relations that paint a better overall picture for me, and lead me to better questions and follow up actions.