kyeb

(disclaimer: I work at Falconer)

you would think so! but that's only optimal if the model already has all the information in recent context to make an optimally-informed decision.

in practice, this is a neat context engineering trick, where the different LLM calls in the "courtroom" have different context and can contribute independent bits of reasoning to the overall "case"

Falconer | Lead AI engineer | Bay area, hybrid/onsite | $200-300k + equity

Falconer is building AI-powered knowledge tools for engineers. Knowledge management is a $30b industry, and we intend to build the tools that leverage AI to power the next generation of engineering knowledge. Our vision is to empower every engineer to write as well as the best technical writers, and enable every organization to have internal docs as great as the best external docs are.

We're currently a team of 8 from Stripe and Meta, currently turning our prototype into a generally available product.

Looking for an engineer experienced in evals, inference latency optimization, prompt caching, and LLM agent reliability. Or someone who just loves tinkering with the latest models and newly-published techniques, and wants to work somewhere you try them out in a real product that people use!

Apply at https://falconer.com/jobs, or drop your resume and a sentence or two about what AI knowledge workflows you would be excited to work on to jobs@falconer.ai

- Learn their default layout first, then iterate on your personal preferences. I similarly tried a bunch at first, but realized switching layouts constantly was making it impossible to build up the new muscle memory.

- Spend time practicing away from important coding tasks (e.g. gaming, writing, a side project, a one-off script, etc.). Being able to learn in a forgiving environment, outside of deadlines, gives you the space to allow mistakes and time to correct them

I find one modifier plus a home-row key to be much more comfortable than reaching several rows up for an F-key.

The author's whole point here is that QMK (or ZMK, which I use) lets you customize it to exactly your own needs!

Falconer | Founding team (AI, infrastructure) or early-career engineers (any) | Bay area, hybrid/onsite | $125-250k

Falconer is building AI-powered knowledge tools for engineers. Knowledge management is a $30b industry, and we intend to build the tools that leverage AI to power the next generation of engineering knowledge. Our vision is to empower every engineer to write as well as the best technical writers, and enable every organization to have internal docs as great as the best external docs are.

We're currently a team of 5 from Stripe and Meta, prototyping the product with design partners, and hiring a few more engineers to round out the founding team. We've raised a $5m seed round and have several customers lined up, we just need to build it!

Apply at https://falconer.ai/careers, or drop your resume and a sentence or two about what AI knowledge workflows you would be excited to work on to jobs@falconer.ai!

Falconer | Founding team (AI, infrastructure, full-stack, designer) | Bay area, hybrid/onsite | $150-200k

Falconer is building AI-powered knowledge tools for engineers. Knowledge management is a $30b industry, and we intend to build the tools that leverage AI to power the next generation of engineering knowledge. Our vision is to empower every engineer to write as well as the best technical writers, and enable every organization to have internal docs as great as the best external docs are.

We're currently a team of 4 from Stripe and Meta, prototyping the product with design partners, and hiring a few more engineers to round out the founding team. We've raised a $5m seed round and have several customers lined up, we just need to build it!

Apply at https://falconer.ai/careers, or drop your resume and a sentence or two about what AI knowledge workflows you would be excited to build to jobs@falconer.ai!

Falconer | Founding team (AI, infrastructure, full-stack, designer) | Bay area, hybrid/onsite | $150-200k

Falconer is building AI-powered knowledge tools for engineers. Knowledge management is a $30b industry, and we intend to build the tools that leverage AI to power the next generation of engineering knowledge. Our vision is to empower every engineer to write as well as the best technical writers, and enable every organization to have internal docs as great as the best external docs are.

We're currently a team of 3 from Stripe and Meta, prototyping the product with design partners, and hiring a few more engineers to round out the founding team. We've raised a $5m seed round and have several customers lined up, we just need to build it!

Apply at https://falconer.ai/careers, or drop your resume and a sentence or two about what AI knowledge workflows you would be excited to build to jobs@falconer.ai!

Falconer | Founding team (AI, infrastructure, full-stack, designer) | Bay area | Hybrid/onsite

Falconer is building AI-powered knowledge tools for engineers. Knowledge management is a $30b industry, and we intend to build the tools that leverage AI to power the next generation of engineering knowledge. Our vision is to empower every engineer to write as well as the best technical writers, and enable every organization to have internal docs as great as the best external docs are.

We're currently a team of 3 from Stripe and Meta, prototyping the product with design partners, and hiring a few more engineers to round out the founding team. We've raised a $5m seed round and have several customers lined up, we just need to build it!

Apply at https://falconer.ai/careers, or drop your resume and a sentence or two about what AI knowledge workflows you would be excited to build to jobs@falconer.ai!

What makes you say it's a "left-wing culture war item"? I've gotten the impression opposition to using AI-generated content like this typically comes from artists who might have been paid for similar content in the past

The calls per server is probably not the difficult part - this is the type of scale where you start hitting much, much harder problems, e.g.:

- Load balancing across regions [0] without significant latency overhead

- Service-to-service mesh/discovery that scales with less than O(# of servers)

- Reliable processing (retries without causing retry storms, optimistic hedging)

- Coordinating error handling and observability

All without the engineers actually writing the functions needing to know anything about the system (which requires airtight reliability, abstractions, observability).

I don't mean to comment on whether this is impressive or not, just pointing out that per-server throughput would never be the difficult part of reaching this scale.

[0] And apparently for this system, load balancing across time, which is at least a mildly interesting way of thinking about it

It sounds like this is about direct carbon cature, not carbon offsets.

It would have solved it completely for my family - we just ate cereal or a bagel in the morning for breakfast, no coordination necessary.

I'd be super interested to see an analysis using exactly the same methodology as this performed on various other cities (SF, NYC, LA, maybe some European cities like Amsterdam or Cologne) for comparison. I would bet Seattle is near the top for the US in walkability (probably behind NYC only)

There are some legitimate concerns about Warp throughout these comments (telemetry, business model, etc.).

But the one thing that really excites me is to have a full team working full-time on building the terminal that developers want to use. They're doing real user research, talking to developers, and taking feedback in forums like HN seriously - and using up millions of VC-dollars building a new version of this fundamentally important core utility. I'd much rather have that VC money go toward an attempt at a better terminal than some ML or web3 startup.

I think this doesn't usually happen? All the terminal emulators I've used usually open-source projects developed in someone's free time. Don't get me wrong, projects like Alacritty, urxvt, xterm, Terminator etc. are amazing for the funding they have (I think mostly $0?), but I'm super excited to see what a cohesive terminal based on real UX research can look like.

I don't think anyone was implying that causal link...

Airbnb hosts rate their guests. Seems like a decent system to me.

The interesting part about this idea to me is the scalability.

If you're someone looking to cold-email someone you admire, you're willing to spend a dollar to do that.

If you're a spammer who plays number games with your emails (maybe 0.01% result in a successful clickthrough), $1 per email is not even close to worth it.

I haven't thought through all the consequences yet, but this seems like a super interesting idea to me, with the potential to kill off the low-probability-of-success emails that I get hundreds of per day!

This is horrifying.

As a computer scientist who learned JavaScript this year, I strongly agree with the sentiment here. I feel like I often spend more time debugging module errors than my actual project.

Granted, once I understood the ecosystem more, I gradually began to grasp the reason these issues are around. But still, it does make it incredibly frustrating as a reasonably decent coder getting started in JavaScript.

AutoHotKey was my first programming language, years and years ago on my couple hundred dollar laptop. It wasn't much, but it was definitely a great introduction to basic CS concepts (if statements, loops, functions, etc.).

I remember using it to automate login for a variety of websites, and to automate resource collection for a game I played (Lord of Ultima, in case anyone remembers it).

I just skimmed much of their website, and felt like I was left still wondering what Backstage actually does.

We have 1 kitchen in the basement, but that's shared among 500 people

The closest grocery is Target in Central square, which is extremely limited or maybe Trader Joe's, which also isn't the same. The Star Market that was right behind campus closed a couple years ago. It's not so easy, in my opinion.

MIT is kind of a weird location. Cambridge and Boston are _very_ high cost of living. Plus, every dorm either has kitchens or a dining hall, so the food needs aren't super high typically.

>In what way are dorms worse than personal homes for diseases anyway? Are they not trusting their students to prepare their own food? Why don't they just close the dining halls instead?

The dorms have shared bathrooms, often shared rooms with doubles, triples, and quads, and shared living spaces (lounges, study rooms, laundry, etc.) in addition to the dining halls. Moreover, in our dorms, we have effectively no way to eat if the dining halls close down. Since mine has a dining hall for us to eat, it has only one kitchen for the entire dorm, which is ~500 people.

Edit: It's also worth pointing out that MIT students are at very low risk right now. Sending us all home before we're at a medium/high risk level is the right move, so students aren't bringing it home with them. Nobody on campus has tested positive yet (as far as we know), and once it reaches the campus it would spread like crazy. Better to preempt it and send us away now.

I tried to read this article, but unfortunately the lack of grammar was too distracting and I just couldn't get through it.

A lot of these are things that Google Docs or Microsoft Word will notice and ask you to change. I highly recommend using one of those to write (especially if English is not your first language) and trying to understand the suggestions it makes. Your articles will come out much more readable to others.

Wow, I've been reading Axios as my primary news source for years - first time I've seen it linked on HN, though!

I highly recommend it to other people here. The reporting tends to be smart and to the point, their UI/UX is smooth and modern, and their ads tend to be more subtle than similar news sites.

I would love to see more streets like this.

Could someone expand on why Rust "isn't a systems language"?

Wow! I worked next to an intern team this past summer that was attempting to build SandDance into Azure Data Studio - super cool to see a big press release from Microsoft mentioning an intern project as one of the major places SandDance is available to use, especially only less than 2 months after it was handed off to the full-time employees.