Yesterday I asked a question about a Claude Code setting inside Claude Code, don't recall which, and their builtin documentation skill—something like that—ended up doing a web search and found a wrong answer on a third party site. Later I went to their documentation site and it was right there in the docs. Wonder why they can't bundle an AI-friendly version of their own docs (can't be more than a few hundred KBs compressed?) inside their 174MB executable.
It's insane that they concluded the builtin introspection skill for claude documentation should do a web search instead of simply packing the correct documentation in local files. I had the same experience like you, wasting tokens and my time because their architecture decision doesn't work in practice.
I have to google the correct Anthropic documentation and pass that link to claude code because claude isn't able to do the same reliably in order to know how to use its own features.
They used to? I have a distinct memory of it doing exactly that a few months ago. Maybe it got dropped in the mad dash that passes for CC sprint cycles
I’m at 19186/233259, about 0.082, and I’m pretty sure most of my higher upvoted comments are on the shorter side, and my wall of texts tend to not deviate much from 1 karma, sometimes even negative. Don’t put too much stock into fake internet points.
And I really need to waste less time here, didn’t expect to be top 1500…
Claude Code’s subscription pricing is pretty ridiculously subsidized compared to their API pricing if you manage to use anywhere close to the quota. Like 10x I think. Crazy value if you were using $400 in tokens.
I just upgraded to the $100 a month 5x plan 5 minutes ago.
Starting in October with Vscode Copilot Chat it was $150, $200, $300, $400 per month with the same usage. I thought they were just charging more per request without warning. The last couple weeks it seemed that vscode copilot was just fucking up making useless calls.
Perhaps, it wasn't a dark malicious pattern but rather incompetence that was driving up the price.
I try GitHub Copilot every once in a while, and just last month it still managed to produce diffs with unbalanced curly braces, or tried to insert (what should be) a top-level function into the middle of another function and screw up everything. This wasn’t on a free model like GPT 4.1 or 5-mini, IIRC it was 5.2 Codex. What the actual fuck? Only explanation I can come up with is that their pay-per-request model made GHC really stingy with using tokens for context, even when you explicitly ask it to read certain files it ends up grepping and adding a couple lines.
You're not using the good models and then blaming the tool? Just use claude models.
Copilot's main problem seems to be people don't know how to use it. They need to delete all their plugins except the vscode, CLI ones, and disable all models except anthropic ones.
The Claude Code reputation diff is greatly exaggerated beyond that.
What, 5.2 Codex isn’t a good model? Claude 4.5 and Gemini 3 Pro with Copilot aren’t any better, I don’t have enough of a sample of Opus 4.5 usage with Copilot to say with confidence how it fares since they charge 3x for Opus 4.5 compared to everything else.
If Copilot is stupid uniquely with 5.2 Codex then they should disable that instead of blaming the user (I know they aren’t, you are). But that’s not the case, it’s noticeably worse with everything. Compared to both Cursor and Claude Code.
Agree, but it seems dependent on field. One day I wanted a browser extension made, and 5.2-codex-max added hundreds of lines of code several times, and for 15-20 iterations I did not change one thing, or even have an opinion on what it was doing. This is extremely uncommon for other models for me, even Opus I would say. And yes, I mostly do small green-field things and not even that works all the time, even if LLMs are clearly at their best there.
I had my first go at using it (Github Copilot) last week, for a simple refactoring task. I'd have to say I reasonably specified it, yet it still managed to to fail to delete a closing brace when it removed the opening block as specified.
That was using the Claude Sonnet 4.5 model, I wonder if using the Opus 4.5 model would have managed to avoid that.
It's really a spectrum. Some were kidnapped. Some knew part of the what they were getting into (they're there to scam people) but were lured by the promise of high salary, but later found out it wasn't what was promised and lost freedom. Some knew exactly what they were getting into, are voluntarily there, and even have personal freedom. Not every scam syndicate in the general area treat every scammer the same. It's often hard to tell who is in what category.
I always assumed Meta has backdoor that at least allows them to compromise key individuals if men in black ask, but law firm representing NSO courageously defending the people? Come the fuck on.
> Our colleagues’ defence of NSO on appeal has nothing to do with the facts disclosed to us and which form the basis of the lawsuit we brought for worldwide WhatsApp users.
These representations are legally binding. If Meta were intentionally lying on these, it would invite billions of dollars of liability. They use similar terminology as Signal and the best private VPN companies: we can't read and don't retain message content, so law enforcement can't ask for it. They do keep some "meta" information and will provide it with a valid subpoenoa.
The latter link even clarifies Meta's interpretation of their responsibilities under "National Security Letters", which the US Government has tried to use to circumvent 4th amendment protections in the past:
> We interpret the national security letter provision as applied to WhatsApp to require the production of only two categories of information: name and length of service.
I guess we'll see if this lawsuit goes anywhere or discovery reveals anything surprising.
Open source models can be hosted by provider, in particular plenty of educational institutions host open source models. You get to choose whatever provider you trust. For instance I used DeepSeek R1 a fair bit last year but never on deepseek.com or through its API.
You're not counting the money they paid to Adam Neumann to walk away, which was over a billion dollars as well.
Imagine doing what was effectively fraud, building a cult around you, everything going completely to the fan, and then the team you defrauded turns around and gives you a billion dollars.
And then, you get Marc Andreesen to write you a $350 million check not too long after.
> Finally, taking an OpenSSL public API and attempting to trace the implementation to see how it is implemented has become an exercise in self-flagellation. Being able to read the source to understand how something works is important both as part of self-improvement in software engineering, but also because as sophisticated consumers there are inevitably things about how an implementation works that aren’t documented, and reading the source gives you ground truth. The number of indirect calls, optional paths, #ifdef, and other obstacles to comprehension is astounding. We cannot overstate the extent to which just reading the OpenSSL source code has become miserable — in a way that both wasn’t true previously, and isn’t true in LibreSSL, BoringSSL, or AWS-LC.
Also,
> OpenSSL’s CI is exceptionally flaky, and the OpenSSL project has grown to tolerate this flakiness, which masks serious bugs. OpenSSL 3.0.4 contained a critical buffer overflow in the RSA implementation on AVX-512-capable CPUs. This bug was actually caught by CI — but because the crash only occurred when the CI runner happened to have an AVX-512 CPU (not all did), the failures were apparently dismissed as flakiness. Three years later, the project still merges code with failing tests: the day we prepared our conference slides, five of ten recent commits had failing CI checks, and the day before we delivered the talk, every single commit had failing cross-compilation builds.
Even bugs caught by CI get ignored and end up in releases.
Wow, that is just crazy. You should investigate when developing software, but for something like OpenSSL... Makes me think this must be a heaven for state actors.
reply