Software developers are not okay.#llm #chatgpt #aihttps://www.baldurbjarnason.com/2026/05-software-developers-are-not-ok...
Software developers are not okay.#llm #chatgpt #aihttps://www.baldurbjarnason.com/2026/05-software-developers-are-not-okay/
15909 articles tagged with LLM
Software developers are not okay.#llm #chatgpt #aihttps://www.baldurbjarnason.com/2026/05-software-developers-are-not-okay/
The public issue trackers of the major agent CLIs are the best place to read what "my agent got...#ai #memory #llm #productivity #software #coding #development #engineering #inclus...
One thing to keep in mind is that LLM training is always lagging behind. Any change, any improvement/fix in practices, regulations is not necessarily taken into account (except if ...
Evaluating agents by outcomes alone can obscure the capabilities that produce them. This problem is especially pronounced in evolving environments, where outcomes reflect a closed-...
Developers confronting their go-to LLM/AI assistant about their database design and terrible database server performance...not realizing everything it 'knows' was learned from othe...
Release: llm-openai-decisions 0.1a0 OpenAI released their new Jev-style Decisions API, as previously announced at last week's DevDay. Since I already have an llm-typesafe plugin fo...
LLMs may have helped my RSIhttps://vaughanhilts.me/2026/10/05/llms-immensely-helped-my-rsi.html#llm #llms
Watching the kernel conf on LLM and security, the dev in the room clearly uses LLMs all day long while saying it's bad. Let's call it LLimux, be clear. FSF is happy to destroy copy...
Most of what we build at work has a cost profile that barely moves. A server, a database and a...#ai #llm #architecture #saas #software #coding #development #engineering #inclusive...
Release: llm-mistral 0.16 Adds support for reasoning models, such as the newly released Mistral Large 4. Tags: llm, mistral, llm-reasoning
I'm building NaHero (https://nahero.site) on my own. It's a set of timed practice exams for AWS,...
TL;DR Some agent failures can be proven from the trace alone, such as a tool call that violates its...
JEV is getting a lot of attention right now. People are excited about it, and developers are...#agents #ai #llm #software #coding #development #engineering #inclusive #community10 ...
TL;DRThe KV cache is often the real memory ceiling in LLM serving, not the weights. Quantizing it to FP8 or INT8 roughly halves KV memory, which lets you serve longer contexts or m...
艦長とバルトさんは、富山については意見が合わないようです泉鏡花賞に荒俣さんら https://www.47news.jp/15045410.html#Apple #LLM #news #bot
Ook ChatGPT-teksten krijgen onzichtbaar 'watermerk'#AI #LLM https://nos.nl/artikel/2633893-ook-chatgpt-teksten-krijgen-onzichtbaar-watermerk
I don't disagree with Gergely Orosz's assessment, which is basically LLM/Agent coding doing everything is the inevitable endpoint. I just find it incredibly depressing and disgusti...
“Is this code malicious?”#LLM #AI #Morals #ethics https://www.manifold.security/blog/do-models-consider-morality-malware
She used Claude as a diary. The terms of service are now part of the charge. ...#ai #claude #llm #privacy #software #coding #development #engineering #inclusive #communitycheck thi...
What is disaggregated prefill and decode in LLM inference? Prefill is compute-bound, decode is...
MoFlux is an admission-control layer that sits in front of an inference engine. It protects capacity...#llm #ai #performance #mlops #software #coding #development #engineering #inc...
1. The Siren Song of Universal Protocol NormalizationEvery backend engineer who builds an LLM proxy experiences the same architectural epiphany:"Why maintain three separate routing...
なぜ今、OWASP Top 10 for LLM Applications 2026を読むべきか 第2回 https://www.yayafa.com/2904212/ #AgenticAi #AI #ArtificialGeneralIntelligence #ArtificialIntelligence #LLM #NTTデータ #NTTデータ先端技術 ...
Запустил собственный PII-фильтр перед облачными моделями и отказался от идеи селф-хостед LLMЗа последние 2 месяца я протестировал RTX PRO 6000 96GB / RTX4090 48GB и даже H200, оцен...