ilia-a

Trying to address the long-standing issue of un-safe deserialization by introducing built-in hmac into PHP serialization process and at the same time improving general performance (now better or equal to igbinary)

Unfortunately at the moment the model is very quickly burning through plans, single session with 3-4 subagents, none using Max or Xhigh, mostly medium + some High can burn through 5h limit within 20-40 minutes of usage.

DuckDB is really neat, recently added PDO interface for it for PHP https://github.com/iliaal/pdo_duckdb

Still a bit raw, but getting there

First of all there is a way to made agents spot truncation by being aware of RTK compression and having bypass option (I use RTK_DISABLE=1) as a way of restoring original full text.

Works fine, yeah it only compresses command output so only input tokens are affected in terms of "compression".

PHP

I did fill the form our a while back (it was around for a few months now) without any response. I guess must be really big OSS project for maintainer to qualify.

Seems odd limit, especially since it highly dependant on Token provider used, with Opus this is not much and could easily be burnt in a week or less, but with something like deepseek the 1500 can literarily be an annual budget.

That being said, I do have to wonder why someone as bug as say Uber, simply not rollout OSS model in the cloud for their team, I'd imagine that would be cheapest & most flexible option, while also keeping all the data shared with LLM private.

I mean they are comparing themselves to Haiku of all things, geez that's not a good start...

Because of the memory costs lately, I doubt this will be much cheaper. Also this is quite a bit slower than even 4070 let alone *90 Nvidia variants albeit with much lower memory.

Looks like just rebranded DGX in laptop form, the biggest miss is the weak memory speed, 1/2 of the M5 laptop memory speed, and 1/3 of the M3 ultra that is now years old...

Yeah, it is a massive jump in price, hardly a "Flash" model anymore... I wonder if they'll release flash lite or something with a bit more affordable price point.

Native PHP extension: 19 chart types behind a fluent OO API, plus Code 128 barcodes and QR codes sharing the same gd substrate. Composable: charts can draw into a caller-owned GdImage canvas, so multiple charts composite onto one image in a single render pass. PHP 8.3+, BSD-licensed.

IMHO Mythos was more of a marketing ploy.

When it comes to security and AI, all top tier publicly accessible models (GPT 5.5, Opus 4.7) and even near-top like Deepseek 4 PRO can do a very good job given detailed harness on how to spot issues and cross-validate them to avoid false positives.

Looks like lots of grift going on.

Forgetting other categories for a moment, the fact that corp operations are nearly 2x the money going to linux kernel says it all...

I wonder how much shared hosting is there really left, I imagine much of it move to VPS or cheap cloud boxes.

Original online communities (forums/chat rooms) got largely killed by social media, now social media is getting killed by AI slop.

Another nail in the web anonymity sounds like

Interesting that the 5h limits are raised, but if I understand announcement correctly, the weekly limit is not. So all this means is that you can burn through your weekly limit faster and be locked out entirely, or having to buy tokens

Even without writing code LLMs are a huge help, analyzing code, doing code reviews, documenting code, etc... Even without writing a line of "code" LLM hugely speed up development and take away the annoying/boring work.

Compared to what was before and after it was pretty great.

Windows 10, especially when they added WSL2 was genuinely great and an awesome platform for development, with essentially native/fast Linux. Since Win11, it has all been downhill (imo), speed dropped massively, even opening task manager now takes seconds, weird slowdowns that only reboot resolves (temporarily). I hope Microsoft starts taking performance seriously and tries to get back to what was lost after Win10, but I have big doubts.

Seems kinda obvious, given that most large recruiting firms/hr use algos to analyze resumes and AI written version likely do a better job at hitting keywords/structure algos/llms pick up on...

That doesn't seem right and seems to miss GLM 5.1 and Kimi 2.6. Not to mention there is the whole argument of cost/value that Chinese OSS models have vs GPT/Claude.

I use codex plugin to often validate claude results, surprisingly many findings, so for things like code-review becomes very helpful. Considering trying using Deepseek 4 Pro, seems like could be a good/cheap alternative to codex

Not surprising, hit my 5h limit on Claude Code Max Plan, had some credits so switched to extended (api). 40 minutes later $30 credits gone... so yeah, I can see how this can happen.

Yeesh, first kernel root exploit, now this...

Low key wonder if people using LLMs to scan these old code bases for corner case issues and fining treasure troves of exploits.

Silly move since combo of skills/agents can achieve same results on most recent models anyway