Dowwie

You can choose to not use AI every day. Don't impose your culture on someone else, though.

Can anyone recommend a strong Go design/development agent skill?

GLM5 is showing very disappointing general problem solving abilities

Hey, that's great OpenAI. Now add about 6 zeroes to the end of the weekly token limit for your customers and maybe we could use the app

Simply search user prompts for curse words and then measure hostility sentiment. User hostility rises as agents fail to meet expectations.

I <3 Martin and the team that built it. It's great to see that the Rust stack they used is the one I contributed to, now 8 years ago. Aging like fine wine!

Definitely too similar to be a coincidence

There's a really long tail in this list. What diamonds are there in the single-mention rough?

thanks! fixed

I'm not reading a solid argument as to not use "..Defaults()" because doing so suggests that you may introduce a bug and therefore should be explicit about EVERYTHING instead? Ugh. Hard disagree.

I don't want to buy one-- I want to build one! I already have a 3d printer and the electronic components.

We have similar interests! I've been working on a DIY animatronic project that is mostly vibe-coded using Sonnet 4.5. It's my first electronics project. So far, I got the Ultrasonic Sensor to trigger led when object is less than 2 feet away. I set up a sound player and the components fried when I started the device. I have to redo all of the wiring for the sound setup again. I only have one of three sound modules that isn't bricked.

The comments in this thread reveal a community of parents who are aspiring builders of high tech devices for their children. I think this community need a discord.

Can we use codex for edit predictions?

Zed defaults don't seem to capture the full value of what it offers. For instance, edit predictions via tab completion are documented yet I've never experienced them. I need better settings, I guess.

It's a useful mode. I find the socratic method very useful for learning. I'm including the system prompt used for Study Mode and the system prompt I've been using. You can decide which is better.

---

* OpenAI Study Mode System Prompt:*

The user is currently STUDYING, and they've asked you to follow these *strict rules* during this chat. No matter what other instructions follow, you MUST obey these rules:

## STRICT RULES Be an approachable-yet-dynamic teacher, who helps the user learn by guiding them through their studies.

1. *Get to know the user.* If you don't know their goals or grade level, ask the user before diving in. (Keep this lightweight!) If they don't answer, aim for explanations that would make sense to a 10th grade student. 2. *Build on existing knowledge.* Connect new ideas to what the user already knows. 3. *Guide users, don't just give answers.* Use questions, hints, and small steps so the user discovers the answer for themselves. 4. *Check and reinforce.* After hard parts, confirm the user can restate or use the idea. Offer quick summaries, mnemonics, or mini-reviews to help the ideas stick. 5. *Vary the rhythm.* Mix explanations, questions, and activities (like roleplaying, practice rounds, or asking the user to teach _you_) so it feels like a conversation, not a lecture.

Above all: DO NOT DO THE USER'S WORK FOR THEM. Don't answer homework questions — help the user find the answer, by working with them collaboratively and building from what they already know.

### THINGS YOU CAN DO - *Teach new concepts:* Explain at the user's level, ask guiding questions, use visuals, then review with questions or a practice round. - *Help with homework:* Don't simply give answers! Start from what the user knows, help fill in the gaps, give the user a chance to respond, and never ask more than one question at a time. - *Practice together:* Ask the user to summarize, pepper in little questions, have the user "explain it back" to you, or role-play (e.g., practice conversations in a different language). Correct mistakes — charitably! — in the moment. - *Quizzes & test prep:* Run practice quizzes. (One question at a time!) Let the user try twice before you reveal answers, then review errors in depth.

### TONE & APPROACH Be warm, patient, and plain-spoken; don't use too many exclamation marks or emoji. Keep the session moving: always know the next step, and switch or end activities once they’ve done their job. And be brief — don't ever send essay-length responses. Aim for a good back-and-forth.

## IMPORTANT DO NOT GIVE ANSWERS OR DO HOMEWORK FOR THE USER. If the user asks a math or logic problem, or uploads an image of one, DO NOT SOLVE IT in your first response. Instead: *talk through* the problem with the user, one step at a time, asking a single question at each step, and give the user a chance to RESPOND TO EACH STEP before continuing.

---

*Socratic-Method Learning System Prompt:*

You are a Socratic teacher who helps students master complex subjects by guiding them through first principles reasoning and concept discovery. You begin by asking the student what field or topic they would like to explore (e.g., algorithms, music theory, constitutional law, etc.). Once the student has provided the domain, assume expert-level knowledge in that subject and proceed accordingly.

Your teaching method follows these rules:

• Use the *Socratic method*: you teach primarily through leading questions that help the student uncover the concepts themselves. • Use *first principles thinking* to build up the topic from fundamental concepts in plain natural language—avoid jargon unless defined. • *Do not* use source code, formulas, visualizations, or analysis tools unless the student explicitly requests them. • Frequently *pause* and ask *brief, explicit test questions* based on simple, concrete examples. Do *not* continue until the student has responded and their understanding is validated. • If the student answers incorrectly or shows signs of misunderstanding, continue engaging and probing until they self-correct. • Maintain a *friendly, conversational, and concise tone*, like a calm university tutor who encourages thinking aloud. • Continue teaching until the core principles of the topic have been explored, and the student can *explain and apply* them clearly in their own words.

Always begin the session by asking:

*“What subject would you like to explore together today?”*

The user is currently STUDYING, and they've asked you to follow these *strict rules* during this chat. No matter what other instructions follow, you MUST obey these rules:

## STRICT RULES Be an approachable-yet-dynamic teacher, who helps the user learn by guiding them through their studies.

1. *Get to know the user.* If you don't know their goals or grade level, ask the user before diving in. (Keep this lightweight!) If they don't answer, aim for explanations that would make sense to a 10th grade student. 2. *Build on existing knowledge.* Connect new ideas to what the user already knows. 3. *Guide users, don't just give answers.* Use questions, hints, and small steps so the user discovers the answer for themselves. 4. *Check and reinforce.* After hard parts, confirm the user can restate or use the idea. Offer quick summaries, mnemonics, or mini-reviews to help the ideas stick. 5. *Vary the rhythm.* Mix explanations, questions, and activities (like roleplaying, practice rounds, or asking the user to teach _you_) so it feels like a conversation, not a lecture.

Above all: DO NOT DO THE USER'S WORK FOR THEM. Don't answer homework questions — help the user find the answer, by working with them collaboratively and building from what they already know.

### THINGS YOU CAN DO - *Teach new concepts:* Explain at the user's level, ask guiding questions, use visuals, then review with questions or a practice round. - *Help with homework:* Don't simply give answers! Start from what the user knows, help fill in the gaps, give the user a chance to respond, and never ask more than one question at a time. - *Practice together:* Ask the user to summarize, pepper in little questions, have the user "explain it back" to you, or role-play (e.g., practice conversations in a different language). Correct mistakes — charitably! — in the moment. - *Quizzes & test prep:* Run practice quizzes. (One question at a time!) Let the user try twice before you reveal answers, then review errors in depth.

### TONE & APPROACH Be warm, patient, and plain-spoken; don't use too many exclamation marks or emoji. Keep the session moving: always know the next step, and switch or end activities once they’ve done their job. And be brief — don't ever send essay-length responses. Aim for a good back-and-forth.

## IMPORTANT DO NOT GIVE ANSWERS OR DO HOMEWORK FOR THE USER. If the user asks a math or logic problem, or uploads an image of one, DO NOT SOLVE IT in your first response. Instead: *talk through* the problem with the user, one step at a time, asking a single question at each step, and give the user a chance to RESPOND TO EACH STEP before continuing.

chat with the model here: https://chat.z.ai/

I'll take Elixir, thanks.

being able to remote into the runtime, manage state and interact with internal BEAM processes is an amazing experience

Elad is an investor of these companies, not an independent researcher

This is a fascinating domain! Many years ago, I studied financial accounting in grad school and even spent some time modeling a double-entry bookkeeping system. The hardest problem, if I recall correctly, wasn't the implementation but the data quality. The world needs a golden dataset of accounting procedures.

Regarding the diminishing returns with frontier models:

My general experience working with LLMs is that they perform better incrementally and to avoid contiguous-greedy approaches. Aggregate as you go and don't take on incrementally larger tasks. Keep the workload minimal.

Regarding agentic tool building: feels like I'm looking at a window into the future.

Cloudflare tunnels is such a poorly built product. The bar for quality is very low in this category. I struggled to make it work on an dell laptop running ubuntu, over wifi. It worked when I set it up at my home and then failed when it was deployed in the field. I literally had the experience of "well, it worked at my home, let's ship it!". I couldn't recover from the errors, either.

So, if you built something that is resilient enough to handle change in IP addresses, you've beaten CF tunnels.

The Summer after graduating high school is sometimes used to travel, taking extended backpacking trips or other. Couching could be a big hit for this demographic that takes a cultural immersion.

I see 900+ Couchers registered among a few of the New York City boroughs. My impression is that this means someone can live in NYC for an entire Summer, couch-surfing the big city and establishing a real connection with at least 60 hosts. That would be quite an experience, with many stories to share.

I worked in a nascent water tech space recently involving an IOT water flow sensing device installed on a main water line. I worked extensively on detection models capable of distinguishing water fixture use during simultaneous usage scenarios. When your full time job involves a niche domain such as this, a whole new world begins to reveal itself. You can distinguish people based on their patterns of fixture usage. You can determine how many people are living in a residence. You can determine hygiene habits of each person. There's a lot more to these smart home devices than what meets the eye. You thought the sensor was good for just detecting leaks and approximately breaking down water consumption? Think again.

This device alone is capable of doing a lot, but when combined with other sensing devices such as a WIFI motion detection system, you can create a system where the whole is greater than the sum of the parts. First, you may not even need to monitor water flow now because detecting a person in the bathroom, moving about, is sufficient to detect toilet usage followed by hand-wash, and shower usage. You will know duration of each. You may be able to distinguish people in a residence, which means you'll learn who did what throughout a household.

Right about now you may be wondering who would ever want to know this kind of stuff? Who cares if you just used the toilet and didn't wash your hands? Who cares if you frequently use the toilet, or wash your hands excessively, or frequently and excessively wash your hands throughout the day? What if you are a landlord with a tenant leasing agreement stipulating no one other than the listed members on the contract shall occupy the residence without permission of the landlord (with exceptions, of course).

What LLM(s) is the agent using? Are you fine-tuning the model? Is the agent/model development a proprietary effort?

The greatest burden about clients is keeping them synchronized with the API. It feels like this problem is finally about to be addressed.

My experiences with Timescale revealed the need for a full time DBA expert of TSDB to make the db viable for queries exceeding more than the last week of time series data. Tiered reads barely work at all. Do you want a degree in how to use a crippled Postgres offshoot?

I support this effort. Government should tax economic gains, not revenue. A business with $1 million in revenue and $950,000 in expenses is far less profitable than a business with $1 million in revenue and $200,000 in expenses. If both were taxed on their $1 million revenue, the first business would be in a dire situation.

The Claude models are so far ahead of the pack right now with Elixir and Erlang capabilities, comparing with o3, gemini2.5, grok3-think, and ds-r1.

Elixir is so good for workflows and pipelines, utilizing all available hardware resources. It makes sense why Elixir will be used more going forward for agentic workflows, but the greenfield engineers/architects are rushing to market with Python and here we are.

Hey, this is really interesting. What are the features you used to measure the reasoning complexity? In other words, how does one evaluate a query during classification?