Semipro

Computer geek, Co Creator of first IM, Group Chat system and former X-League (X-1) football player, A.P.P.L.E. (

[Gunther Eagleman™ @GuntherEagleman]

🚨 SECWAR JUST ADMINISTERED THE REENLISTMENT OF MARINE LEGEND STAFF SERGEANT JOHNNY JOEY JONES!

The Department of War making it official, one of America’s greatest living heroes is back in uniform.

From machine gunner in Iraq to EOD tech in Afghanistan… losing both legs to an IED in Helmand… fighting through recovery at Walter Reed… and never stopping his service to this country.

Now he’s re-enlisting.

[Semipro @semipro]

@0xPrajwal_ I fully agree...Had to buy Max just to get real work done. DONT BUY PRO....IT SUCKS!

[Kashaf @noor36758]

@ravikiran_dev7 $20 plan hitting like a free trial since weeks.... fix it Anthropic 😭💀

[Ray🫧 @ravikiran_dev7]

Dear Anthropic, please fix the Claude Code usage limits bug asap.

$20 plan feels like a free plan since weeks.

[Semipro @semipro]

@bridgemindai Weekly limit going at 12% per 5 hr. session. 5Hr usage going at 1-2 Opus 4.7 requests on the Pro Plan. Useless for really doing any real work.

[Semipro @semipro]

That night work for you the MAX users but the PRO users are still being throttled and limited like crazy. 1-2 requests = 100% of 5 hr and about 12% on average of Weekly. (is @AnthropicAI lying to us?)

[BridgeMind @bridgemindai]

I might never hit my Claude Code rate limits again.

After yesterday's Anthropic x SpaceXAI deal, peak hour rate limits are being removed completely.

5 hour limits are increasing by 100%.

I did not see this coming.

I cancelled my Claude Max plan twice over rate limits.

I switched to Codex.

Now Anthropic gets access to one of the largest supercomputers on the planet and overnight the rate limit problem is disappearing.

If this holds, Claude Code is back.

This is insane.

[Semipro @semipro]

Definitely a nope....was 100% of the 5hr

[Semipro @semipro]

A whole lot of NOPE! I am not seeing it. 2 requests on Opus 4.7 kills 80% of the 5 hour usage on Pro? That is not doubled and certainly not usable.

[Claude @claudeai]

We’ve agreed to a partnership with @SpaceX that will substantially increase our compute capacity.

This, along with our other recent compute deals, means that we’ve been able to increase our usage limits for Claude Code and the Claude API.

[Semipro @semipro]

@claudeai @SpaceX STILL NOT SEEING THE SO CALLED DOUBLING. USED ALL MY 5 HOUR WITH 1 REQUEST!!!

[A Man Of Memes @RickyDoggin]

Let Racism Die The Death It Deserves

[Steve Skojec @SteveSkojec]

He’s dead on.

[End3of6Days9 (Helen) 🇺🇸 @end3of6days9]

This guy created an automated script that calls back spam callers and absolutely torments them.

When they answer, it blasts them with an endless loop of Rick Astley’s “Never Gonna Give You Up”… and then it keeps calling them back again and again until the spam company is forced to block his number — which is exactly what he wants.

I’m convinced this guy created a million dollar idea and he should turn this into a real app!

Sometimes the best way to deal with life’s little annoyances is with clever creativity and a good sense of humor — turning frustration into something that actually makes you smile.

Have you ever wished you could get sweet revenge on those endless spam callers?

[Semipro @semipro]

@ClaudeDevs What about the extra funds that we all used for these buggy models?

[⚓️ Sailor Jim 🔱 @JimHendley4NC]

They just thought Pete Hegseth was over the top, now we have a man in charge of the Navy who blew shit up for 30+ years and was really good at it.

A great time to be alive!
Congratulations @HungCao_VA

[Semipro @semipro]

@bridgemindai That happens almost every time on Pro during the week. On the weekends I might get 4 requests. The least amount of usage on 4.6 or 4.7 I have gotten is 73% in one shot.

[Semipro @semipro]

That's Great but 93% on the 5 hour usage gone with one debug request. Hmmmmm...Not sure that makes me want to put any more real money to it beyond the Subscription.

[Claude @claudeai]

Introducing Claude Opus 4.7, our most capable Opus model yet.

It handles long-running tasks with more rigor, follows instructions more precisely, and verifies its own outputs before reporting back.

You can hand off your hardest work with less supervision.

[Semipro @semipro]

@bcherny It would be nice if Opus 4.6 wasn't so useless burning through nearly 100% on 1 request or Sonnet 4.6 burning through 25% in 1 request. 4.5 level models not even available in the App to scale down.

[Semipro @semipro]

Just a little bit of typical western Washington weather with a lot of hail in a hurry

[BridgeMind @bridgemindai]

Claude Code is unusable.

So I built my own.

Introducing BridgeCode.

Launching next Wednesday.

Everything you love about Claude Code.

No rate limits. No 529 errors. No 500 errors.

No nerfing.

Connect to any provider.

Claude Opus 4.6. GPT 5.4. Gemini 3.1 Pro. GLM 5.1.

All of them. Switch models in seconds.

And one more thing.

Swarm mode. One prompt. Ten agents.

Working together to ship your code.

Claude Code rate limited me into building a competitor.

Thank you, Anthropic.

Launching next Wednesday.

https://t.co/ANnI8HyjJ6

[Semipro @semipro]

@bridgemindai I am beginning to wonder if they aren't in violation of U.S. advertising laws and whether it could become one of the biggest class action lawsuits ever for false advertising.