thelittleone

Sadly only allows sign up with Github.

Not clear on site if it integrates third parties for test automation.

You also get things like Stripe with mandatory arbitration. The arbitrator is chosen by Stripe. Naturally arbitrator wants to keep Stripe as a client.

Stripe terms allow them to hold the funds until 'investigation' is concluded but while held, they have the right to invest the funds and keep the profit.

It's baffling that gift cards are so popular. You're essentially paying to decrease the value of your own money by restricting its use and adding an expiration date (and handing to someone as a gift as if it's a thoughtful alternative to cash).

An even more egregious case is the corporate credit card. The company dictates its use exclusively for business expenses, yet pushes all the liability onto the employee. The business gets a massive, interest-free credit line with absolutely no risk. The company gets the float, and the employee gets the bill and the potential credit damage if anything goes wrong.

</rant>

That's good fathering. Respect.

I'd enjoy watching. A new category of eSports.

The context usage awareness is a bit boost for this in my experience. I use speckit and have setup to wrap up tasks when at least 20% of context remaining with a summary of progress, followed by /clear, insert summary and continue. This has reduced compacts almost entirely.

That's probably true, but whereas before I hit max 200. Limits once a week or so. Now I have multiple projects running 16hrs a day some with 3-4 worktrees, and haven't hit limits for several weeks.

My test a few hours ago. Ultra plan got me ~20 minutes with Antigravity using Gemini 3 Pro (Low) before zero out.

With Ultra I hit that limit in 20 minutes with Gemini 3 low. When the rate limit cleared some hours later, I got one prompt before hitting limit again.

early gmail invite codes went for like $100 if I recall correctly..

Agree, breakfast slows me down, so I rarely eat it anymore and typically eat around midday to 1pm after morning work and exercise. I've fasted only once, it lasted 12 days and my energy level was almost overwhelming and electric. Boxing, running, etc. I gave up trying to understand why. And although it was an amazing experience, have not fasted again in the 5 years since.

Is it able to isolate the speaker from background noises / voices?

I stopped nebido cold turkey, went on HMG and HCG by subcutaneous injection 3 days a week. Had a few chills and sweats at first, but mood impact was not noticeable. No change to training routine (HiiT, boxing muay thai and calisthenics). A few months along, I switched to enclopmiphene citrate (25mg daily).

I was on TRT for 10 years. Then I met an amazing woman, we wanted to start a family. Fertility clinic confirmed 0 sperm production. 6 months later she, she fell pregnant.

Wow hadn't even considered this... so say I have a members only section of my site where I share high value content, one of the members browses using Comet, and that scrapes the private content and sends to perplexity?

Hey Patrick,

When your algorithm freezes a legit business's funds, you hold them indefinitely and can invest them for your own profit. The only recourse you offer is mandatory arbitration with an arbitrator Stripe chooses.

How is that a fair system?

I found a boost adding LikeC4 to the spec.

Jira is working for me via atlassian MCP.

Interesting. Works with claude max or API only?

I've had same experience. Taskmaster-ai was pretty good, but sometimes the agent ignored it as the project grew larger (can probably prevent that now using claude code hooks).

Trying this project today looks nice. I see you have sub-tasks. Any thoughts on a 'dependency' relation? I.e., don't do X if it is dependent on task A which is not complete.

FYI, there is a 404 in the AGENTS.md GEMINI.md etc pointing to a non existing README.md.

This also:

1) Assign coding task via prompt 2) Hook: Write test for prompt proves 3) Write code 4) Hook: Test code 5) Code passes -> Commit 6) Else go to 3.

In some cases cc misses rules in CLAUDE.md.

The cost on paper may be cheaper. But those options become less attractive when you take into account timezones, communication challenges, availability, scheduling, and the ever increasing coding performance of coding agents.

Wow... name collision avoidance is applied across the solar system.

Respect for taking the time to apply for his recognition.

But... but... he's innocent... can't you tell from his Ghibli avatar?

Different experience here. Production code in banking and finance for backend data analysis and reporting. Sure the code isn't perfect, but doesn't need to be. It's saving >50% effort and the analysis results and reporting are of at least as good a standard as human developed alternatives.

Full blown OS is a valid option, but installing and maintaining a full blown OS with the equivalent of their ecosystem apps is more complex and time consuming. Some will consider that a PITA and that audience likely isn't bothered by a crippled Linux.

Sleep walker per chance?

Regarding context reduction. This got me wondering. If I use my own API key, there is no way for the IDE or coplilot provider to benefit other than monthly sub. But if I am using their provided model with tokens from the monthly subscription, they are incentivized to charge me based on tokens I submit to them, but then optimize that and pass on a smaller request to the LLM and get more margin. Is that what you are referring to?