Joel Puig

2.3K posts

Joel Puig

Joel Puig

@puigru

Programador i amant de l'anime en Català

Katılım Mayıs 2020
512 Takip Edilen183 Takipçiler
Joel Puig
Joel Puig@puigru·
@zack_overflow One of the most annoying traits of coding LLMs. GPT 5.5 does this too, even Opus 4.5 did.
English
0
0
0
36
zack
zack@zack_overflow·
Noticing Fable is very often writing code comments that reference details from chatting with it, but they make very little sense in the context of reading it in the codebase
English
99
11
1.7K
87.3K
Joel Puig
Joel Puig@puigru·
@thdxr I've been working on something quite similar. Hope to publish soon enough
English
0
0
0
412
dax
dax@thdxr·
issue comes in tag opencode opens a PR with a video verifying fix
dax tweet media
English
19
7
453
77.3K
Petr Samokhin
Petr Samokhin@petersamokhin·
@levelsio @NStoronsky he's not gonna read it here I'm afraid 🥲 I'm gonna ping bros at Premium department because it'd be a huge win for Revolut if the relevant product owner will appear here in replies
English
1
0
19
2.8K
@levelsio
@levelsio@levelsio·
Revolut cuts off your eSIM after 4 months to avoid "bill shock" (???) That means you'll eventually end up in the middle of nowhere with no data, no way to top up your data (cause you need data for that), literally useless So you can't ever use it as your main telephone carrier! I have no idea who is running the eSIM department at @Revolut nor what they are smoking, don't you want my money?
@levelsio tweet media
@levelsio@levelsio

eSIM renewal is still broken on @Revolut @NStoronsky Whatever you set to renewal, it has never actually renewed and it leaves you with no data in the middle of nowhere And lots of missed $$$ for you

English
137
23
1.5K
348.9K
Joel Puig
Joel Puig@puigru·
@disconcision Codex does this too. If you leave it in an agentic loop long enough, it will start correcting itself and leave cruft like this eveywhere.
English
0
0
0
42
andrew blinn in sf ⏱️
andrew blinn in sf ⏱️@disconcision·
why is claude like this (ask to remove something; leaves tombstone-like comment saying thing was removed)
andrew blinn in sf ⏱️ tweet media
English
86
16
1.6K
92K
Joel Puig retweetledi
Univers Lost Media
Univers Lost Media@UniversLM·
Sabies que molts doblatges en català de les sèries i pel·lícules de quan eres petit estan en risc de desaparèixer? ⏳📼 @UniversLM neix amb un objectiu clar: recuperar i salvar aquest material audiovisual que avui dia és Lost Media. Dins vídeo! 👇🍿 youtu.be/vs275dCqv_0
YouTube video
YouTube
Català
1
18
24
1.9K
ThioJoe
ThioJoe@thiojoe·
⚠️ WARNING ⚠️ - It is ILLEGAL to purchase digital-only goods using a delaware zip code, just to avoid the sales tax (even if you don’t live there). Just because the address you use makes no difference for digital goods, does NOT mean you may just completely dodge the taxes!
English
106
100
4K
642K
InsForge
InsForge@insforge·
Introducing InsForge Compute. Deploy long-running backend services as Docker containers via your coding agent. It writes the Dockerfile, builds the image, injects env vars, runs the container, and returns a live URL. All in under 60 seconds.
English
35
30
208
1.5M
Joel Puig
Joel Puig@puigru·
@airkatakana I am concerned about the promotional 10x usage expiring for the $100 plan though, because it would push me into the $200 plan territory. Otherwise I've not managed to use more than 30% weekly in a single day so far
English
2
0
1
377
Joel Puig
Joel Puig@puigru·
@airkatakana The 15% was burned in the single night vibecoding session. I had 30% left at the start, meaning I'd used 70% during the week and have another ~15% left until it resets tonight
English
1
0
1
411
Air Katakana
Air Katakana@airkatakana·
when the codex $200 plan came out it was advertised as “unlimited use subject to abuse guardrails”. and at the time it was true now we’ve powercreeped so much that 5.5 xhigh fast in goal mode can burn the whole thing in one day, off of one prompt
English
37
6
554
40.5K
Joel Puig
Joel Puig@puigru·
@MitakaEdwardVz Ah, ya me parecía raro xd. No sabía que hubiese un teclado Canadiense
Español
1
0
1
46
Joel Puig retweetledi
Joel Puig
Joel Puig@puigru·
Això és molt perillós. Vull canviar-me el telèfon per un que no sigui depengui dels serveis de Google ni tampoc Apple, però ho fan impossible. Avui dia t'exclouen del sistema bancari pràcticament.
GrapheneOS@GrapheneOS

Apple and Google are gradually expanding their use of hardware-based attestation. They're convincing a growing number of services to adopt it. Google's Play Integrity API and Apple's App Attest API are very similar. Apple brought it to the web via Privacy Pass, which Google intends on doing too. Google's Play Integrity API requires hardware attestation for the strong integrity level and is gradually phasing in requiring it for the more commonly used device integrity level. Apple already has it as a requirement. Over the long term, this will increasingly lock out hardware and OS competition. The purpose of these systems is disallowing people from using hardware and software not approved by Apple or Google. This is wrongly presented as being a security feature. Banks and government services are the main ones adopting it but Apple and Google are encouraging every service to use it. Apple's Privacy Pass brought hardware attestation to the web to help with passing captchas on their own hardware. Many people saw that as harmless since few sites would be willing to lock out non-Apple-hardware users. Apple and Google are both likely to bring broader hardware attestation to the web. Google's reCAPTCHA is planning an approach where they use Privacy Pass on Apple hardware, their own approach on Google Mobile Services Android devices and a QR code scanning system to require an iOS or Google certified Android device for Windows and other systems: support.google.com/recaptcha/answ… Banking and government services increasingly require using a mobile app where they can use attestation to force using an Apple or Google approved device and OS. Apple's privacy pass, Google's 'cancelled' Web Environment Integrity and now reCAPTCHA Mobile Verification are bringing this to the web. Current media coverage for reCAPTCHA Mobile Verification misunderstands it and the impact of it. They're bringing a hardware attestation requirement to Windows, desktop Linux, OpenBSD, etc. by requiring a QR scan from a certified smartphone to pass reCAPTCHA in some cases. They could expand it more. Control over reCAPTCHA puts Google in a position where they can require having either iOS or a certified Android device to use an enormous amount of the web. Google defines certification requirements for Android which includes forcing bundling Google Chrome, etc. It's enormously anti-competitive. Google's Play Integrity API bans using GrapheneOS despite it being far more secure than anything they permit. It also bans using any other alternative. This isn't somehow specific to an AOSP-based OS. You can't avoid this by using a mobile OS based on FreeBSD instead. You'll just be more locked out. Google's Play Integrity API permits devices with no security patches for 10 years. The device integrity level can be bypassed via spoofing but they can detect it quite well and block it once it starts being done at scale. The strong integrity level requires leaked keys from TEEs/SEs to bypass it. It doesn't provide a useful security feature, but it does lock out competition very well. Services requiring Apple App Attest or Google Play Integrity are primarily helping to lock in Apple and Google having a duopoly for mobile devices. Play Integrity is more relevant due to AOSP being open source. Governments are increasingly mandating using Apple's App Attest and Google's Play Integrity for not only their own services but also commercial services. The EU is leading the charge of making these requirements for digital payments, ID, age verification, etc. Many EU government apps require them. Instead of governments stopping Apple and Google from engaging in egregiously anti-competitive behavior, they're directly participating in locking out competition via their own services. Requiring people to have an Apple device or Google-certified Android device is anti-competition, not security. reCAPTCHA Mobile Verification will currently work with sandboxed Google Play on GrapheneOS but it clearly exists to provide a way for them to start using hardware attestation on systems without it. People without an iOS or Android device will be locked out when this is required even without that. This isn't about security or any missing functionality. GrapheneOS can be verified via hardware attestation. Google bans using GrapheneOS for Play Integrity because we don't license Google Mobile Services and conform to anti-competitive rules already found to be illegal in South Korea and elsewhere. Services shouldn't ban people from using arbitrary hardware and operating systems in the first place. Google's security excuse is clearly bogus when they permit devices with no patches for 10 years but not a much more secure OS. It's for enforcing their monopolies via GMS licensing, that's all.

Català
6
1
78
7.1K
Joel Puig
Joel Puig@puigru·
@lalgorisme Ostres, estava pensant en fer-me una eina de l'estil. Moltes mercès per la recerca!
Català
0
0
3
619
L’algorisme
L’algorisme@lalgorisme·
🧵 Les empreses porten anys filtrant CVs amb IA fent q milers de candidats mai arribin a ser entrevistats. Ara la gent ha après a fer el mateix a l'inrevés: usar IA per filtrar empreses, descartar, avaluar ofertes i maximitzar les possibilitats de trobar feina. Van tres eines:
Català
4
73
230
20.4K
Joel Puig
Joel Puig@puigru·
És ridícul que @Ryanair @Ryanair_ES hagi de fer servir un software de text a veu per a les instruccions de seguretat en català mentre que en altres idiomes hi posi veu una persona
Català
1
0
1
141
Joel Puig retweetledi
Theo - t3.gg
Theo - t3.gg@theo·
It is genuinely insane that Anthropic will bill you differently if you mention certain words in your prompt or have certain files in your codebase
Om Patel@om_patel5

THIS GUY LOST $200 IN ONE DAY BECAUSE THE STRING "HERMES.md" WAS IN HIS GIT COMMITS HERMES.md is a real convention used in AI agent projects. it's a system prompt specification file. not some obscure edge case he's on claude max 20x at $200 a month. yesterday claude code hit him with "you're out of extra usage" out of nowhere his dashboard showed 13% weekly usage. 0% current session. 86% of his plan was sitting there untouched but $200.98 in extra usage already burned through what should have been covered by his subscription he tried logout & login, different models, fresh installs and nothing worked anthropic support sent the ai bot (four rounds of the same scripted response). eventually they just gave up on him so he started binary searching repos and commits manually on his own time until he found the trigger the string "HERMES.md" in a recent git commit message uppercase, with the .md extension, anywhere in your commit history that's it claude code includes recent commits in its system prompt and something server side flags HERMES.md and quietly routes you off your max plan onto API rate billing > AGENTS.md? fine > README.md? fine > HERMES without .md? fine > lowercase hermes.md? fine > uppercase HERMES.md? you're getting charged API rates he reported it. anthropic support acknowledged the bug three times, called it an "authentication routing issue", thanked him for finding it then refused to refund the $200 so the man pays $200 a month for max, lost another $200 to a billing bug they confirmed, did anthropic's QA work for free on his weekend, and got a "thank you for your patience" in return check your commit history before claude code quietly drains your account too

English
177
145
3.7K
353.8K
Joel Puig
Joel Puig@puigru·
@jordimash Doncs encara no et sé dir. Em va arribar tot just ahir, aquest cap de setmana el configuro. Ja t'ho faré saber 😉
Català
1
0
2
17
Jordi Mas
Jordi Mas@jordimash·
@puigru Ah, quina enveja. Estàs content amb les prestacions?
Català
1
0
1
22