Notes

Ken writes about the lessons they’ve learned building new LLM-based features into their product. When it comes to prompts, less is more Not enumerating an exact list or instructions in the prompt produces better results, if that thing was already common knowledge. GPT is not dumb, and it actually gets confused if you over-specify. This has been my experience as well. For a recent project, I first started with a very long and detailed prompt, asking the LLM to classify a text and produce a summary. GPT-4, GPT-3.5, Claude-3-Opus, and Claude-3-Haiku all performed average or poorly. I then experimented with shorter prompts, and with some adjustments I was able to get much better responses with a very much shorter prompt. ...

“Luck” is one of the most interesting topics to me, and I always find myself paying extra attention to anyone talking about what “luck” is and how it can be somehow controlled. Morgen makes a useful distinction between “lucky” and “repeatable” traits: … a better way to frame luck is by asking: what isn’t repeatable? Did Jeff Bezos get lucky creating Amazon? Not in the same way a lottery winner is lucky, of course. He was visionary and ambitious and savvy to a degree you only see a few times per century. ...

This is a fantastic reminder from Herbert: If you want to do something, like really want to do it, you need to prove it. That starts with you proving it to yourself. In difficult circumstances, do you make excuses? Or do you face your problem head on? Are you willing to make difficult decisions to do what you’ve committed to? Are you willing to put out bad work in order to improve? Are you open to taking feedback—even if it hurts—in order to improve? ...

Them: Can you just quickly pull this data for me? Me: Sure, let me just: SELECT * FROM some_ideal_clean_and_pristine.table_that_you_think_exists source

Melody is basically describing me: Many introverts value depth and thoughtfulness in their work over noise and showmanship. They’re content to contribute without constant recognition or the spotlight. And the consequences part also checks out: While this tendency is admirable, it comes with pitfalls, especially in the modern, remote-first work world where being “out of sight” often equates to being “out of mind.” Perhaps you’ve been overlooked for a promotion because a senior leader wasn’t aware of you or your accomplishments. Or maybe your quiet demeanor has been mistaken for a lack of passion. These experiences may have awakened you to the fact that in today’s competitive workplace, hard work isn’t enough. You need to make sure your efforts are seen and acknowledged to unlock new opportunities and support. ...

After reading this post from Lara, I finally understand why I’ve been feeling strangely uncomfortable whenever my work desks have been moved in the past. Here are humans’ core needs in the BICEPS model: Belonging Community: A feeling of friendship and closeness with a group, or being part of a tight community of any size. Community well-being: People are cared for, the whole group feels happy and healthy. Connection: Feeling kinship and understanding with Improvement/Progress Progress towards purpose: You are helping make progress towards an important goal for the company, your team or your own career/life. Improving the lives of others: You see how your work helps improve things for others Personal growth: Learning/seeing fast growth in yourself in skills that matter to you. Choice Choice: Having flexibility, the chance to have more control over key parts of your world Autonomy: Having clear ownership over a domain where you can do as you wish, without asking for permission Decision-making: The ability to have make decisions about the things that matter to you Equality/Fairness Access to resources (money, time, space, etc) feels fair/equitable Access to information is fair: All groups/people have access to information that is relevant to them Equal reciprocity: You support each other equally Decisions are fair and everyone is treated as equally important Predictability Resources: There’s enough certainty about resources (money, personnel hours, space) so you can focus on your job Time: There’s certainty about when things will occur/when you can prepare for them. Future challenges: You can anticipate and thus can prepare for future challenges Direction: Goals, strategy, and direction stay consistent and don’t change too often/fast Status Status: You hold a title/role that honors your worth among your peers/your industry Visibility: Your work is highly visible to people that matter Recognition: Your work is recognized and appreciated in ways that feel good. source ...

Every day a new tools pops out claiming “Throw the data analysts and data scientists of your company away, you don’t need to write SQL anymore, everyone can use data with our groundbreaking ’talk to your data’ tool”, and Benn discusses this: There are thousands of computational devils in details like how to handle nulls. For analysts, describing these specifics in English is inefficient and inexact. For everyone else, they wouldn’t know they need to describe them at all. ...

From a hackernews thread on dealing with spammers on your platform: … one of the most effective ways of dealing with spammers is to “shadowban” them. Allow them to use your service, but don’t indicate to them that you’ve identified them as malicious. For instance, when dealing with chat spammers, allow them to chat, but do not show their chats to other users. Another level would be to allow them to chat, but only show their chat to other shadowbanned users. … If the malicious actor doesn’t know they’ve been marked as malicious, they do not know they need to change their behavior. ...

A few days ago a question was asked on Hackernews on how slow thinkers compensate for their lack of quick-wittedness . Some people have responded that preparation is key: Sometimes what people think is quickness is actually extensive prep. I had a 30 minute meeting the other day to ask a team to do something I didn’t think they would want to do. It ended up going really smoothly and they just took my word for it, but had they not, I spend several hours preparing for that meeting, gathering data, preparing charts to illustrate the data, thinking of the possible objections and responses to said objections. ...

Many companies are integrating LLM question answering tools into their DevEx toolchain. If you’re writing documentation and you’d like to assist these tools to serve people with proper responses to the questions related to what you own, kapa.ai has a few practical tips on optimizing the technical docs for LLMs: A clear hierarchy of headings and subheadings on a page helps LLMs understand the relationships between different sections of your documentation. Troubleshooting sections formatted as Q&A are an effective source for LLMs as they mirror the questions users often ask, making it easier for LLMs to understand and respond to similar questions. Including small, self-standing code snippets can be helpful, especially for products that rely on large and often complex SDKs or APIs. Have a brief description above the code to clarify its purpose and usage. Include comments within the code to explain the logic and functionality. Keep relevant content directly in your docs rather than in linked files such as PDFs, as LLMs have a harder time parsing these. Ensure information conveyed through screenshots is also described in text, as LLMs parse text more efficiently. Clarify all acronyms and specialized terminology within your documentation to aid LLM comprehension. source ...

This post from Dan is one of the best reads in the past few months for me. He openly talks about instances that he might look like a stupid person, and how it’s benefiting him. I highly recommend reading the full blog post . … I frequently ask questions when there’s something I don’t understand or know, from basic stuff, “what does [some word] mean?” to more subtle stuff. On the flip side, one of the most common failure modes I see with junior engineers is when someone will be too afraid to look stupid to ask questions and then learn very slowly as a result; in some cases, this is so severe it results in them being put on a PIP and then getting fired. ...

If you’re into either Alfred or Raycast , Josh has a nice comparison of these tools from his experience using them: … for me, in the era of paid subscription software overtaking everything, I don’t need yet another $8–10/month siphon on my bank account. By the time you’ve paid for Raycast Pro for a year, you could’ve paid for Alfred for a lifetime. I absolutely agree. Due to Alfred being a one-time purchase and its wonderful speed and performance, I tend to agree with Josh that: ...

Hamel dives deep into how LLM frameworks like langchain , instructor , and guidance perform tasks like formatting the response in a valid JSON output. He intercepts the API calls from these Python libraries to shed some light on how many API calls (to OpenAI’s GPT services) they make and what prompt they use. I’ve always been skeptic of the usefulness of many of the LLM “wrapper” libraries, specially for larger and more serious projects, as they are fine for quick prototypes. ...

I came across this Linkedin post from a Google engineer, on a new (in preview) and very interesting BigQuery syntax: GROUP BY ALL. This will save time when writing and specially modifying complex SQL queries on BigQuery. The GROUP BY ALL clause groups rows by inferring grouping keys from the SELECT items. It will exclude expressions with aggregate and window functions, constants, and query parameters for a smart GROUP BY. So instead of GROUP BY name, city, device, browser, date or GROUP BY 1, 2, 3, 4, 5 you would use GROUP BY ALL. ...

For small web projects that you don’t want to get large CSS frameworks like Tailwind to be involved, the classless CSS libraries can be very handy. You just 1-2 lines into the head of the html and get beautifully styled pages. Here are a few classless CSS libraries you can use: concrete.css water.css pico css simple css classless.de mvp.css NES.css drop-in minimal css Usage example To use water.css , just paste this into the <head> of your HTML: ...

I stumbled upon a hackernews thread where people have recommended many interesting tools to help with generating color palettes for various use cases. I’m creating this list for my future self, and will add other options whenever I come across one. uicolors.app : I’ve used this one when working on redesigning the user interface for my latest side project. The nice feature of uicolors.app is its Tailwind export functionality which allows you to quickly export the color palette as a Tailwind config code snippet. tints.dev : Palette Generator + API for Tailwind CSS colorjs.io huemint.com adevade.github.io/color-scheme-generator colorcolor.in colormind.io paletton.com huehive.co : Generate palettes with ChatGPT source ...

There is a huge gap in generative AI between the quality you observe when you’re playing with it open endedly, and the quality you observe when you try to use it for a task where you have a specific end goal in mind. This is I think where most of the hype/reality mismatch occurs. This accurately sums up my experience using generating AI in a daily base and building products with this technology. ...

If you need another reason to hate office politics, Dave Anderson shares some awful advice on how to join office politics, one of them is: Slow down other teams If other teams move quickly, your team can become a bottleneck. That never looks good. When a wild animal is chasing you, you need to not be the slowest. Slow down your peer teams by asking for info, or starting processes. As a bonus, you look as if you’re holding a high bar. ...

Manu writes about apps and businesses who claim to replace search engines by feeding the web page content to a language model and returning the response to the user: Firstly, without a search engine in the mix, the AI has no way to search for anything. So if the goal is to replace the traditional search engine then we’re already failing. Because we’re not replacing anything, we’re just hiding it behind some AI tool. ...

Herbert Lui writes about his experience getting writing feedback from editors: My editors were giving me comments and suggestions on all of these posts, but I noticed a tension: as I accepted these changes and resolved comments, they would effectively disappear into a basement-equivalent dropdown menu, never to see the light of day again. I would lose the majority of the feedback that I received. But it’s difficult to learn from your mistakes if you don’t reflect on them. He then starts logging the feedbacks he receives: ...