Geoff Flarity

And the universe said: "Hold my beer!"
Blog - -

[Geoff Flarity @gflarity]

This didn't age well.

[Geoff Flarity @gflarity]

Saw this on linkedin, but the guy was lighting the cigar himself. I fixed it using ChatGPT.

[Geoff Flarity @gflarity]

@nejatian @HamedBarkh @nejatian, so tempted to apply just to make you laugh at the resume I'd put together. What an amazing time and what a great recruitment idea. Love it

[nolen @itseieio]

made a hook that adds a bouncing dvd logo to claude code whenever it's thinking

[Geoff Flarity @gflarity]

In 2025, just 22.8% of people with a disability were employed vs 65.2% for those without. The unemployment gap widened: disability rate rose to 8.3% (+0.8 pts) while non-disability rate hit 4.1% (+0.3 pts). #BLS #JobsReport

[Geoff Flarity @gflarity]

🚨#PPI Update: Producer prices rose 0.5% in Jan 2026 (up 2.9% YoY). Services surged 0.8% driven by wholesale margins, but goods fell 0.3% as energy prices dropped. Core PPI (ex-food/energy/trade) up 0.3% for 9th straight month, now +3.4% YoY. #Inflation #Economy

[Geoff Flarity @gflarity]

BREAKING: US labor market saw a net loss of 321,000 jobs in Q2 2025 as losses (7.9M) outpaced gains (7.6M). Losses rose sharply by 668K while gains only grew 137K. 41 states & 9/13 industry sectors experienced net job declines. #BLSdata #JobsReport

[Geoff Flarity @gflarity]

BLS: 30 major work stoppages in 2025 involving 306,800 workers. Education/health services & public administration led with 196,500 and 82,300 idled workers respectively. State & local government strikes accounted for 76% of all idled workers.

[Geoff Flarity @gflarity]

State JOLTS Dec '25: Job openings down in 6 states, led by VT & NH. Total separations rose in 9 states, notably WY & SD. Quits increased in 5 states (SD, WY), fell in 2 (TN, GA). National picture? Little change across the board.

[Geoff Flarity @gflarity]

Union membership held steady at 10.0% of the US workforce in 2025 (14.7M members), per BLS. This rate remains about half of what it was in 1983 (20.1%). #LaborStats #Economy

[Geoff Flarity @gflarity]

BREAKING BLS: Real wages are on the rise! In Jan '26, real average hourly earnings for all employees rose 0.3% month-over-month. Even better, they're up 1.2% year-over-year. Real weekly earnings jumped 1.9% over the past year. A solid gain in worker purchasing power!

[Geoff Flarity @gflarity]

January CPI up 0.2% monthly, 2.4% annually (down from 2.7%). Shelter costs remain the biggest driver, while energy fell 1.5% (gasoline down 3.2%). Core inflation (ex-food/energy) +0.3% monthly, +2.5% yearly. Airfares soared 6.5% in one month! 🛫 #CPI #Inflation

[Geoff Flarity @gflarity]

December 2025 metro jobless rates ⬆��� in 255 of 387 areas year-over-year. National unempl. at 4.1% (from 3.8%). El Centro, CA highest (18.6%), Decatur/Huntsville, AL lowest (1.9% each). Charlotte led job gains (+37.6k), D.C. saw sharpest loss (-55.9k). #BLS #Jobs

[Geoff Flarity @gflarity]

JOLTS Report: Job openings continued to trend down in Dec 2025 to 6.5M. Hires & total separations stable at 5.3M each. Key insight: Quits held at 3.2M, signaling steady worker confidence while the labor market cools. #Jobs #Economy #BLSdata

[Geoff Flarity @gflarity]

NEW BLS DATA: Unemployment rises in most metro areas vs. last year. 259 of 387 areas saw higher jobless rates in Nov '25. Only 100 areas improved. National rate up to 4.3% from 4.0%. Job growth was minimal, with payrolls up in just 8 metro areas. #Jobs #Economy #BLSdata

[Geoff Flarity @gflarity]

JOLTS Report (Nov '25): The labor market held steady 🛑. Job openings were little changed at 7.1M (rate 4.3%). Hires & separations both flat at 5.1M. Quits (3.2M) signal stable worker confidence. #Jobs #Economy #BLSdata

[Geoff Flarity @gflarity]

Don't have a take on most of his questions. Indeed, it'll be interesting to see. But this one seems obvious to me. The answer is YES. Broad generalist benefit are already benefiting the most from what I've seen.

- Armed with LLMs, do generalists increasingly outperform specialists? LLMs are a lot better at fill in the blanks (the micro) than grand strategy (the macro).

[Andrej Karpathy @karpathy]

A few random notes from claude coding quite a bit last few weeks.

Coding workflow. Given the latest lift in LLM coding capability, like many others I rapidly went from about 80% manual+autocomplete coding and 20% agents in November to 80% agent coding and 20% edits+touchups in December. i.e. I really am mostly programming in English now, a bit sheepishly telling the LLM what code to write... in words. It hurts the ego a bit but the power to operate over software in large "code actions" is just too net useful, especially once you adapt to it, configure it, learn to use it, and wrap your head around what it can and cannot do. This is easily the biggest change to my basic coding workflow in ~2 decades of programming and it happened over the course of a few weeks. I'd expect something similar to be happening to well into double digit percent of engineers out there, while the awareness of it in the general population feels well into low single digit percent.

IDEs/agent swarms/fallability. Both the "no need for IDE anymore" hype and the "agent swarm" hype is imo too much for right now. The models definitely still make mistakes and if you have any code you actually care about I would watch them like a hawk, in a nice large IDE on the side. The mistakes have changed a lot - they are not simple syntax errors anymore, they are subtle conceptual errors that a slightly sloppy, hasty junior dev might do. The most common category is that the models make wrong assumptions on your behalf and just run along with them without checking. They also don't manage their confusion, they don't seek clarifications, they don't surface inconsistencies, they don't present tradeoffs, they don't push back when they should, and they are still a little too sycophantic. Things get better in plan mode, but there is some need for a lightweight inline plan mode. They also really like to overcomplicate code and APIs, they bloat abstractions, they don't clean up dead code after themselves, etc. They will implement an inefficient, bloated, brittle construction over 1000 lines of code and it's up to you to be like "umm couldn't you just do this instead?" and they will be like "of course!" and immediately cut it down to 100 lines. They still sometimes change/remove comments and code they don't like or don't sufficiently understand as side effects, even if it is orthogonal to the task at hand. All of this happens despite a few simple attempts to fix it via instructions in CLAUDE . md. Despite all these issues, it is still a net huge improvement and it's very difficult to imagine going back to manual coding. TLDR everyone has their developing flow, my current is a small few CC sessions on the left in ghostty windows/tabs and an IDE on the right for viewing the code + manual edits.

Tenacity. It's so interesting to watch an agent relentlessly work at something. They never get tired, they never get demoralized, they just keep going and trying things where a person would have given up long ago to fight another day. It's a "feel the AGI" moment to watch it struggle with something for a long time just to come out victorious 30 minutes later. You realize that stamina is a core bottleneck to work and that with LLMs in hand it has been dramatically increased.

Speedups. It's not clear how to measure the "speedup" of LLM assistance. Certainly I feel net way faster at what I was going to do, but the main effect is that I do a lot more than I was going to do because 1) I can code up all kinds of things that just wouldn't have been worth coding before and 2) I can approach code that I couldn't work on before because of knowledge/skill issue. So certainly it's speedup, but it's possibly a lot more an expansion.

Leverage. LLMs are exceptionally good at looping until they meet specific goals and this is where most of the "feel the AGI" magic is to be found. Don't tell it what to do, give it success criteria and watch it go. Get it to write tests first and then pass them. Put it in the loop with a browser MCP. Write the naive algorithm that is very likely correct first, then ask it to optimize it while preserving correctness. Change your approach from imperative to declarative to get the agents looping longer and gain leverage.

Fun. I didn't anticipate that with agents programming feels *more* fun because a lot of the fill in the blanks drudgery is removed and what remains is the creative part. I also feel less blocked/stuck (which is not fun) and I experience a lot more courage because there's almost always a way to work hand in hand with it to make some positive progress. I have seen the opposite sentiment from other people too; LLM coding will split up engineers based on those who primarily liked coding and those who primarily liked building.

Atrophy. I've already noticed that I am slowly starting to atrophy my ability to write code manually. Generation (writing code) and discrimination (reading code) are different capabilities in the brain. Largely due to all the little mostly syntactic details involved in programming, you can review code just fine even if you struggle to write it.

Slopacolypse. I am bracing for 2026 as the year of the slopacolypse across all of github, substack, arxiv, X/instagram, and generally all digital media. We're also going to see a lot more AI hype productivity theater (is that even possible?), on the side of actual, real improvements.

Questions. A few of the questions on my mind:
- What happens to the "10X engineer" - the ratio of productivity between the mean and the max engineer? It's quite possible that this grows *a lot*.
- Armed with LLMs, do generalists increasingly outperform specialists? LLMs are a lot better at fill in the blanks (the micro) than grand strategy (the macro).
- What does LLM coding feel like in the future? Is it like playing StarCraft? Playing Factorio? Playing music?
- How much of society is bottlenecked by digital knowledge work?

TLDR Where does this leave us? LLM agent capabilities (Claude & Codex especially) have crossed some kind of threshold of coherence around December 2025 and caused a phase shift in software engineering and closely related. The intelligence part suddenly feels quite a bit ahead of all the rest of it - integrations (tools, knowledge), the necessity for new organizational workflows, processes, diffusion more generally. 2026 is going to be a high energy year as the industry metabolizes the new capability.

[Geoff Flarity @gflarity]

December 2025 jobs report is in! Payrolls increased slightly by 50,000, while the unemployment rate held steady at 4.4%. Gains in food services, health care, and social assistance were offset by losses in retail trade.

[Geoff Flarity @gflarity]

JOLTS Oct '25: Job openings rates up in 3 states (AK, WY, MT), but little change nationally. Hires up in 3 states, tot separations fell in 8. NY lost 40K job openings! #Jobs #Economy #BLSdata