guilamu
Re:Fable Took My Job
on Monday October 12, 2026 @05:46AM (#50053861)
It's à joke. Shrek reference: https://youtu.be/hiKuxfcSrEU?si=anKoBVyhRIegW_X4
Re:Right Click XLSX <-> CSV PowerShell Script
on Friday September 11, 2026 @02:37PM (#49663174)
Extremely useful for me at work, thought I'd share: One 53 KB PowerShell file, 0 dependencies.
Designed by Opus 5, two passes of bug fixes with GPT 5.6 Terra and Kimi k3 at max reasoning effort.
Re:Ads and tracking infiltrated TVs. Now they're coming for monitors
on Tuesday August 25, 2026 @05:26AM (#49431075)
Re:Israel creates fake think tank in likely attempt to dupe AI chatbots
on Tuesday August 18, 2026 @07:01AM (#49343889)
For some reason this page exists only in French, but it says a lot about the credibility of the ADL: https://fr.wikipedia.org/wiki/Anti-Defamation_League#Controv...
YouTube Mistakenly Penalizes Kurzgesagt for AI-Generated Slop
Re:DeepSeek V4 Flash 0731
on Friday August 07, 2026 @04:36PM (#49215923)
Where does this "10x" comes from?
Re:Beginning July 20, Claude Fable 5 will be included in all Max plans
on Saturday July 18, 2026 @12:41PM (#48959696)
FTFY: Starting July 20 Claude Fable 5 will ve excluded from Pro plans.
Re:Phosh 0.56.0
on Sunday July 05, 2026 @09:54AM (#48794339)
Re:Qualcomm Linux 2.0
on Thursday July 02, 2026 @02:02AM (#48757132)
Wouldn't you say that Valve is an exception to that rule?
Re:MiMo-v2.5-Pro-UltraSpeed: 1T model with 1000 tokens per second
on Monday June 08, 2026 @03:35PM (#48450491)
Any source to backup this claim, pretty please?
Re:Oura says it gets government demands for user data
on Saturday May 23, 2026 @12:17PM (#48248897)
If you're concerned about that do not give internet to your tv and use any kind of tv box instead (shield tv, apple tv, etc).
Re:Mistral's CEO: Europe has 2 years to stop becoming America's AI 'va...
on Sunday May 17, 2026 @03:11PM (#48172228)
It's not.
France: €0.149/kWh (~$0.175)
US: ~$0.12–$0.14/kWh
https://www.globalpetrolprices.com/France/electricity_prices...
Re:OpenAI releases GPT-5.5 and GPT-5.5 Pro in the API
on Monday April 27, 2026 @06:02AM (#47919664)
You're right, I've certainly been a bit presumptuous to call this'a benchmark'. It is indeed a flawed test. Yet,It's been giving me the occasion to try some open source models and for my workflow, some of them are incredibly competitive with sota closed source models.
Re:Bob Odenkirk Would Like to Remind You That Life Is a Meaningless Farce
on Monday April 27, 2026 @05:44AM (#47919567)
Most people, including me, beg to disagree. Better Call Saul was a masterpiece.
Re:OpenAI releases GPT-5.5 and GPT-5.5 Pro in the API
on Friday April 24, 2026 @06:10PM (#47896428)
Yeah as I said this a benchmark for my usecase only, a single use case, which is obvisouly not representative of everybody's needs.
What strike me as very strange though is that 0 model were able to just use the search input already present in GravitYForms forms list page and all created a second input.
Also, I know it's not in the prompt, but adding a ctrl+f shortcut to a search input? Is that that crazy? I don't know.
Re:OpenAI releases GPT-5.5 and GPT-5.5 Pro in the API
on Friday April 24, 2026 @04:41PM (#47895498)
https://openrouter.ai/openai/gpt-5.5-pro
30/180 usd on Openrouter. Did I miss something?
Re:OpenAI releases GPT-5.5 and GPT-5.5 Pro in the API
on Friday April 24, 2026 @04:36PM (#47895428)
When nothing is noted it's max reasoning (xhigh in copilot chat in vscode if available).
The models not availble on copilot were tested through opencode (max reasoning) and deepseek v4 was tested through Cline (with max reasoning too).
Re:OpenAI releases GPT-5.5 and GPT-5.5 Pro in the API
on Friday April 24, 2026 @04:30PM (#47895363)
Yes those two models were tested on my own PC (local inference using my own CPU/GPU). So something my be bugged on my setup. gemma4-26b should be far better than gemma4-e4b.
Re:OpenAI releases GPT-5.5 and GPT-5.5 Pro in the API
on Friday April 24, 2026 @04:28PM (#47895353)
Yes, the prompt is slim by design. I might be wrong, but the point was to see what the model can do "on it's own".
The eval prompt is quite extensive: https://github.com/guilamu/llms-wordpress-plugin-benchmark/b...
Re:OpenAI releases GPT-5.5 and GPT-5.5 Pro in the API
on Friday April 24, 2026 @04:25PM (#47895322)
Haha, just fixed the date!
I haven't evaluated the judge benchmark. You have everything needed in the repo to do so though, so be my guest. It took me a bit of time to put all this together and won't have much more time to dedicate to it before a couple of weeks.
BTW, if you explore the repo, sorry for all the French files...
Re:OpenAI releases GPT-5.5 and GPT-5.5 Pro in the API
on Friday April 24, 2026 @04:22PM (#47895291)
Yes Opus 4.7 fast (no reasoning) did a worst job than Sonnet 4.6 high (with reasoning) according to Gemini 3.1 Pro evaluation.
Re:OpenAI releases GPT-5.5 and GPT-5.5 Pro in the API
on Friday April 24, 2026 @04:05PM (#47895122)
Just tested it on my homemade Wordpress+GravityForms benchmark and it's one of the worst model of the leaderboard performance wise and the worst value wise: https://github.com/guilamu/llms-wordpress-plugin-benchmark
I know it's only on a single benchmark, but I dont understand how it can be so bad...
Re:Show HN: I blind-tested 14 LLMs on a WP plugin task. Surprising Fin...
on Friday April 24, 2026 @02:51AM (#47886545)
Good point! I think I won't change anything right now or I'll have to remake all tests...
Show HN: I blind-tested 14 LLMs on a WP plugin task. Surprising Findings
https://github.com/guilamu/llms-wordpress-plugin-benchmark/blob/main/README.md
Recently, GitHub Copilot silently dropped support for Claude Opus on Pro accounts. Since Opus was my go-to model for my daily workflow (developing WordPress plugins), I needed a reliable replacement.I decided to run a rigorous, blind benchmark across 14 state-of-the-art and local LLMs to objectively measure which model understands WordPress development best. To ensure a perfectly fair test, I...
Re:No more Opus for Copilot Pro plan users
on Monday April 20, 2026 @03:14PM (#47839160)
Indeed. I'm still sad thought :(
No more Opus for Copilot Pro plan users
Reasons to think that the Claude Mythos announcement was overblown
Re:Proton Meet Isn't What They Told You It Was
on Friday April 03, 2026 @06:08AM (#47624916)
"Proton Mail, one of the services he moved to, is ultimately controlled by the US Gov,"
Would you mind elaborating, pretty please?
Re:People inside Microsoft are fighting to drop mandatory Microsoft Ac...
on Saturday March 28, 2026 @08:29AM (#47553961)
Why not just get the iso, install, activate with massgravel and be done for life?